技术领域technical field
本发明涉及一种人机界面装置，特别是涉及一种可消除移动背景噪声的光学物体追踪装置及其操作方法。The invention relates to a man-machine interface device, in particular to an optical object tracking device capable of eliminating moving background noise and an operating method thereof.
背景技术Background technique
已知光学物体追踪装置通常包括光源、图像传感器及处理单元；其中，所述光源用以照明接近物体；所述图像传感器用以获取包括所述物体的复数图像帧；所述处理单元则根据所述这些图像帧追踪所述物体的动作。A known optical object tracking device generally includes a light source, an image sensor, and a processing unit; wherein, the light source is used to illuminate an approaching object; the image sensor is used to obtain a plurality of image frames including the object; These image frames track the motion of the object.
然而，所述图像传感器所获取的所述这些图像帧中，除了所述物体图像外，常会另包括有环境光源图像。已知技术中，为了消除所述环境光源图像，所述图像传感器可获取相对所述光源点亮的亮图像帧以及相对所述光源熄灭的暗图像帧，所述处理单元则计算所述亮图像帧及所述暗图像帧的差分图像以消除所述环境光源图像。此种噪声消除方法虽可消除固定环境光源所造成的噪声，然而当所述环境光源的位置随时间改变时，仅单纯计算亮暗图像帧间的差分图像并无法有效消除背景噪声，因而所述处理单元则无法根据所述差分图像正确追踪所述物体的动作。However, in addition to the object image, the image frames acquired by the image sensor often include an image of an ambient light source. In the known technology, in order to eliminate the image of the ambient light source, the image sensor can acquire a bright image frame that is turned on relative to the light source and a dark image frame that is turned off relative to the light source, and the processing unit calculates the bright image frame frame and the difference image of the dark image frame to eliminate the ambient light source image. Although this noise elimination method can eliminate the noise caused by a fixed ambient light source, when the position of the ambient light source changes with time, simply calculating the difference image between bright and dark image frames cannot effectively eliminate the background noise. The processing unit cannot correctly track the movement of the object according to the difference image.
鉴于此，本发明另提出一种物体追踪装置及其操作方法，其可有效消除移动背景所造成的噪声。In view of this, the present invention further proposes an object tracking device and an operation method thereof, which can effectively eliminate noise caused by moving backgrounds.
发明内容Contents of the invention
本发明的目的在于提供一种可消除移动背景噪声的物体追踪装置及其操作方法。The object of the present invention is to provide an object tracking device capable of eliminating moving background noise and an operation method thereof.
本发明提供一种物体追踪装置，包括光源、图像传感器以及处理单元。所述光源以一发光频率发光。所述图像传感器相对所述光源点亮时输出操作图像且相对所述光源熄灭时输出背景图像。所述处理单元用以求出所述背景图像的背景信息、计算所述操作图像与所述背景图像的差分图像、识别所述差分图像中至少一物体及移除所述差分图像中与所述背景信息相关且小于尺寸阈值的无效物体。The invention provides an object tracking device, which includes a light source, an image sensor and a processing unit. The light source emits light with a light emitting frequency. The image sensor outputs an operation image when the light source is turned on and a background image when the light source is turned off. The processing unit is configured to obtain background information of the background image, calculate a difference image between the operation image and the background image, identify at least one object in the difference image, and remove objects in the difference image that are related to the background image. Invalid objects with relevant background information and smaller than the size threshold.
本发明还提供一种物体追踪装置，包括光源、图像传感器以及处理单元。所述光源以一发光频率发光。所述图像传感器相对所述光源点亮时输出操作图像且相对所述光源熄灭时输出背景图像。所述处理单元用以求出所述背景图像的背景信息、计算所述操作图像与所述背景图像的差分图像、求出所述差分图像的物体信息以及比较所述背景信息与所述物体信息以移除背景噪声。The present invention also provides an object tracking device, including a light source, an image sensor and a processing unit. The light source emits light with a light emitting frequency. The image sensor outputs an operation image when the light source is turned on and a background image when the light source is turned off. The processing unit is used to obtain background information of the background image, calculate a difference image between the operation image and the background image, obtain object information of the difference image, and compare the background information with the object information to remove background noise.
本发明还提供一种物体追踪装置的操作方法，包括下列步骤：以图像传感器相对光源熄灭时获取背景图像；以所述图像传感器相对所述光源点亮时获取操作图像；以处理单元求出所述背景图像的背景信息；以所述处理单元计算所述操作图像与所述背景图像的差分图像；以所述处理单元求出所述差分图像的物体信息；以及比较所述背景信息与所述物体信息以移除所述差分图像的背景噪声。The present invention also provides an operation method of an object tracking device, comprising the following steps: obtaining a background image when the image sensor is turned off relative to the light source; obtaining an operation image when the image sensor is turned on relative to the light source; obtaining the obtained image by the processing unit the background information of the background image; calculate the difference image between the operation image and the background image with the processing unit; obtain the object information of the difference image with the processing unit; and compare the background information with the Object information to remove background noise of the difference image.
本发明的物体追踪装置还包括第一储存单元用以储存所述背景图像、所述差分图像、所述背景信息、所述物体信息及/或所述尺寸阈值。The object tracking device of the present invention further includes a first storage unit for storing the background image, the difference image, the background information, the object information and/or the size threshold.
本发明的物体追踪装置及其操作方法中，所述背景信息为至少一背景物体位于所述背景图像的背景物体位置；所述物体信息为至少一物体位于所述差分图像的物体位置。In the object tracking device and its operation method of the present invention, the background information is the background object position of at least one background object located in the background image; the object information is the object position of at least one object located in the difference image.
本发明的物体追踪装置及其操作方法中，还包括第二储存单元储存预设背景图像，其中所述处理单元于计算所述差分图像前先计算所述背景图像与所述预设背景图像的差分背景图像以作为所述背景图像；所述预设背景图像为所述物体追踪装置于开机程序、接受更新命令或检测异常物体时所获取者。In the object tracking device and its operating method of the present invention, a second storage unit is further included to store a preset background image, wherein the processing unit first calculates the difference between the background image and the preset background image before calculating the difference image A differential background image is used as the background image; the default background image is obtained when the object tracking device is booting up, accepting an update command, or detecting abnormal objects.
本发明的物体追踪装置及其操作方法中，所述处理单元将所述差分图像中亮度大于亮度阈值的至少一象素区域识别为所述至少一物体；并将所述背景图像中亮度大于亮度阈值的象素区域识别为所述背景物体。In the object tracking device and its operating method of the present invention, the processing unit recognizes at least one pixel area in the difference image whose brightness is greater than a brightness threshold as the at least one object; and the background image whose brightness is greater than the brightness A thresholded pixel region is identified as the background object.
本发明的物体追踪装置及其操作方法中，当物体的所述物体位置距离所述背景物体位置小于距离阈值且大小小于尺寸阈值时，所述处理单元将所述物体识别为背景噪声或无效物体。In the object tracking device and its operation method of the present invention, when the object position of the object is less than the distance threshold from the background object position and the size is smaller than the size threshold, the processing unit recognizes the object as background noise or an invalid object .
本发明的物体追踪装置及其操作方法中，所述处理单元还根据已移除所述无效物体的所述差分图像进行物体追踪；也就是，根据所述物体位置距离所述背景物体位置大于所述距离阈值的物体进行物体追踪。In the object tracking device and its operation method of the present invention, the processing unit also performs object tracking according to the difference image from which the invalid object has been removed; that is, according to the distance between the object position and the background object position is greater than the Object tracking is performed on objects within the above distance threshold.
本发明实施例的物体追踪装置由于是用以消除移动背景所造成的噪声，因此其优点在于可装设于移动中操作的装置或设备，例如设置于交通工具或可携式电子装置。Since the object tracking device of the embodiment of the present invention is used to eliminate the noise caused by the moving background, it has the advantage that it can be installed in a moving device or device, such as a vehicle or a portable electronic device.
附图说明Description of drawings
图1A及1B显示本发明实施例的物体追踪装置的应用示意图；1A and 1B are schematic diagrams showing the application of an object tracking device according to an embodiment of the present invention;
图2显示本发明实施例的物体追踪装置的方块示意图；FIG. 2 shows a schematic block diagram of an object tracking device according to an embodiment of the present invention;
图3显示本发明实施例的物体追踪装置的操作法的流程图；FIG. 3 shows a flow chart of the operation method of the object tracking device according to the embodiment of the present invention;
图4显示本发明实施例的物体追踪装置的图像获取及光源点亮的示意图；4 shows a schematic diagram of image acquisition and light source lighting of an object tracking device according to an embodiment of the present invention;
图5A-5D显示本发明实施例的物体追踪装置的操作方法的示意图。5A-5D are schematic diagrams showing the operation method of the object tracking device according to the embodiment of the present invention.
附图标记说明Explanation of reference signs
1 物体追踪装置 10 触控面1 Object Tracker 10 Touch Surface
11 光源 12 图像传感器11 Light source 12 Image sensor
13 第一储存单元 14 处理单元13 First storage unit 14 Processing unit
15 第二储存单元 20 背景物体15 Second storage unit 20 Background objects
21 背景物体的位置 20′ 无效物体21 Position of background object 20′ Invalid object
21′ 无效物体的位置 30 物体21′ position of invalid object 30 object
31 物体的位置 7 手指31 Position of objects 7 Fingers
8 可携式电子装置 9 交通工具8 Portable Electronic Devices 9 Vehicles
TH1、TH2 亮度阈值 Io 操作图像TH1 , TH2 brightness threshold Io operation image
Ib背景图像 （Io-Ib）、（Io-Ib）′差分图像Ib background image (Io-Ib), (Io-Ib)' differential image
S11-S17 步骤。S11 -S17 steps.
具体实施方式detailed description
为了让本发明的上述和其他目的、特征、和优点能更明显，下文将配合附图，作详细说明如下。于本发明的说明中，相同的构件是以相同的符号表示，于此预先说明。In order to make the above and other objects, features, and advantages of the present invention more apparent, a detailed description will be given below with reference to the accompanying drawings. In the description of the present invention, the same members are denoted by the same symbols, and will be described in advance.
如图1A及1B所示，其显示本发明实施例的物体追踪装置的应用示意图。由于本发明实施例的物体追踪装置1可用以消除移动背景噪声，因此优选应用于可移动的装置或设备上；例如物体追踪装置1可装设于交通工具9（如图1A）或设置于可携式电子装置8（如图1B）；其中，图1A及1B中所述物体追踪装置1的设置位置仅为例示性。当然，所述物体追踪装置1同样可应用于位置固定的装置或设备上，并不限于图1A及1B所示者。As shown in FIGS. 1A and 1B , they are schematic diagrams showing the application of the object tracking device according to the embodiment of the present invention. Since the object tracking device 1 of the embodiment of the present invention can be used to eliminate moving background noise, it is preferably applied to a movable device or device; for example, the object tracking device 1 can be installed on a vehicle 9 (as shown in FIG. A portable electronic device 8 (as shown in FIG. 1B ); wherein, the installation positions of the object tracking device 1 in FIGS. 1A and 1B are only illustrative. Of course, the object tracking device 1 can also be applied to devices or devices with fixed positions, and is not limited to those shown in FIGS. 1A and 1B .
如图2所示，其显示本发明实施例的物体追踪装置的方块示意图。物体追踪装置1包括触控面10、光源11、图像传感器12、第一储存单元13、处理单元14及第二储存单元15。所述物体追踪装置1是用以针对靠近或接触所述触控面10的至少一物体进行物体追踪并输出追踪信号；其中，所述物体例如可为手指7或触控笔等。所述物体追踪装置1另可包括传输界面用以将所述追踪信号输出至相对应电子装置或设备。As shown in FIG. 2 , it shows a schematic block diagram of an object tracking device according to an embodiment of the present invention. The object tracking device 1 includes a touch surface 10 , a light source 11 , an image sensor 12 , a first storage unit 13 , a processing unit 14 and a second storage unit 15 . The object tracking device 1 is used for object tracking and outputting a tracking signal for at least one object approaching or touching the touch surface 10 ; wherein, the object can be, for example, a finger 7 or a stylus. The object tracking device 1 may further include a transmission interface for outputting the tracking signal to a corresponding electronic device or device.
所述触控面10可由适当材质所制成，其优选相对所述光源11所发出的光为透明。其他实施例中，所述触控面10还可包括滤光器（片），其优选为带通滤光器（bandpassfilter），而仅允许所述光源11所发出光的光谱通过，以避免环境光的干扰。The touch surface 10 can be made of suitable material, which is preferably transparent to the light emitted by the light source 11 . In other embodiments, the touch surface 10 may also include a filter (sheet), which is preferably a bandpass filter, and only allows the spectrum of the light emitted by the light source 11 to pass through, so as to avoid environmental light interference.
所述光源11例如可为至少一发光二极管、激光二极管或其他适当光源，优选以一发光频率发出红光、红外光或其他不可见光，以照明所述手指7。The light source 11 can be, for example, at least one light emitting diode, laser diode or other suitable light source, and preferably emits red light, infrared light or other invisible light at a light emitting frequency to illuminate the finger 7 .
所述图像传感器12例如可为CCD图像传感器、CMOS图像传感器或其他可用以感测光能量的感测器，用以感测反射自所述手指7并穿透所述触控面10的光能量，并相对所述光源11点亮时输出操作图像Io且相对所述光源11熄灭时输出背景图像Ib（在下文详述）。The image sensor 12 can be, for example, a CCD image sensor, a CMOS image sensor or other sensors capable of sensing light energy, so as to sense light energy reflected from the finger 7 and penetrating the touch surface 10 , and an operation image Io is output when the light source 11 is on and a background image Ib is output when the light source 11 is off (detailed below).
所述第一储存单元11用以储存所述图像传感器12输出的背景图像Ib以及所述处理单元14输出的图像资料及运算过程中所需的各种参数，例如差分图像、背景信息、物体信息、尺寸阈值、距离阈值及至少一亮度阈值等（在下文详述）。The first storage unit 11 is used to store the background image Ib output by the image sensor 12 and the image data output by the processing unit 14 and various parameters required in the calculation process, such as difference image, background information, object information , a size threshold, a distance threshold, at least one brightness threshold, etc. (detailed below).
所述处理单元14用以求出所述背景图像Ib的背景信息、计算所述操作图像Io与所述背景图像Ib的差分图像（Io-Ib）、求出所述差分图像（Io-Ib）的物体信息据此识别所述差分图像（Io-Ib）中的至少一物体以及比较所述背景信息与所述物体信息以移除背景噪声，例如移除所述差分图像（Io-Ib）中与所述背景信息相关且小于尺寸阈值的无效物体（也就是所述无效物体将被识别为背景噪声）；其中，所述背景信息为至少一背景物体位于所述背景图像Ib的背景物体位置；所述物体信息为至少一物体位于所述差分图像（Io-Ib）的物体位置。本实施例中，所述处理单元14将所述差分图像（Io-Ib）中亮度大于亮度阈值的至少一象素区域识别为所述至少一物体；或将所述差分图像（Io-Ib）中亮度大于亮度阈值且大于预设尺寸（例如，但不限于3个象素）的至少一象素区域识别为所述至少一物体，而将亮度大于亮度阈值的至少一象素区域且小于所述预设尺寸的象素区域识别为噪声。当所述至少一物体识别出后，所述处理单元14再比较所述背景信息与所述物体信息以将移动背景噪声移除。The processing unit 14 is used to obtain the background information of the background image Ib, calculate the difference image (Io-Ib) between the operation image Io and the background image Ib, and obtain the difference image (Io-Ib) According to the object information, at least one object in the difference image (Io-Ib) is identified and the background information is compared with the object information to remove background noise, for example, remove An invalid object related to the background information and smaller than a size threshold (that is, the invalid object will be identified as background noise); wherein the background information is at least one background object located in the background object position of the background image Ib; The object information is an object position of at least one object located in the difference image (Io-Ib). In this embodiment, the processing unit 14 identifies at least one pixel area in the difference image (Io-Ib) whose brightness is greater than a brightness threshold as the at least one object; or the difference image (Io-Ib) At least one pixel region whose brightness is greater than the brightness threshold and greater than a preset size (for example, but not limited to 3 pixels) is identified as the at least one object, and at least one pixel region whose brightness is greater than the brightness threshold and smaller than the predetermined size is identified as the at least one object. A pixel area of the predetermined size mentioned above is recognized as noise. After the at least one object is recognized, the processing unit 14 compares the background information with the object information to remove moving background noise.
本实施例中，由于背景物体在连续图像间会移动，因此仅计算所述操作图像Io与所述背景图像Ib的差分图像（Io-Ib）并无法完全消除移动背景噪声。因此，本实施例中当一物体的所述物体位置距离所述背景物体位置小于距离阈值且大小小于尺寸阈值时，所述处理单元14则将所述物体识别为所述背景噪声来移除。换句话说，当一物体的所述物体位置距离所述背景物体位置小于距离阈值则定义为与所述背景信息相关，并将所述物体视为无效物体。In this embodiment, since the background object may move between consecutive images, only calculating the difference image (Io−Ib) between the operation image Io and the background image Ib cannot completely eliminate the moving background noise. Therefore, in this embodiment, when the object position of an object is less than a distance threshold from the background object position and smaller than a size threshold, the processing unit 14 identifies the object as the background noise and removes it. In other words, when the object position of an object is less than a distance threshold from the background object position, it is defined as being related to the background information, and the object is regarded as an invalid object.
当所述无效物体移除后，所述处理单元14则可根据已移除所述无效物体的所述差分图像进行物体追踪，例如根据所述物体位置距离所述背景物体位置大于所述距离阈值的所述物体进行物体追踪。由此，由于可完全移除移动背景物体所造成的噪声，故可有效提升物体追踪的正确性。After the invalid object is removed, the processing unit 14 may perform object tracking according to the difference image from which the invalid object has been removed, for example, according to the distance between the object position and the background object position being greater than the distance threshold The object of the object is tracked. Therefore, since the noise caused by moving background objects can be completely removed, the accuracy of object tracking can be effectively improved.
所述第二储存单元15用以储存预设背景图像，所述预设背景图像为所述物体追踪装置1于开机程序、接受更新（背景图像）命令或检测异常物体时所获取的背景图像；也就是，这些程序所获取图像中所包括的物体是为背景噪声，因此所述处理单元14于计算所述差分图像前先计算所述背景图像与所述预设背景图像的差分背景图像以作为所述背景图像。必须说明的是，其他实施例中所述物体追踪装置1可不包括所述第二储存单元15，因此所述处理单元14也不需于计算所述差分图像前先计算所述背景图像与所述预设背景图像的所述差分背景图像。另一实施例中，所述第一储存单元13及所述第二储存单元15可合并为单一储存单元。The second storage unit 15 is used to store a preset background image, and the preset background image is a background image acquired by the object tracking device 1 when it is booting up, receiving an update (background image) command, or detecting an abnormal object; That is, the objects included in the images acquired by these programs are background noises, so the processing unit 14 first calculates the differential background image between the background image and the preset background image as the background noise before calculating the differential image. The background image. It must be noted that, in other embodiments, the object tracking device 1 may not include the second storage unit 15, so the processing unit 14 does not need to calculate the background image and the difference image before calculating the difference image. The differential background image of the preset background image. In another embodiment, the first storage unit 13 and the second storage unit 15 can be combined into a single storage unit.
接着，以下说明本发明实施例的物体追踪装置的操作方法的详细实施方式，其包括下列步骤：以图像传感器相对光源熄灭时获取背景图像（步骤S11）；以所述图像传感器相对所述光源点亮时获取操作图像（步骤S12）；以处理单元求出所述背景图像的背景信息（步骤S13）；以所述处理单元计算所述操作图像与所述背景图像的差分图像（步骤S14）；以所述处理单元求出所述差分图像的物体信息（步骤S15）；比较所述背景信息与所述物体信息以移除所述差分图像的背景噪声（步骤S16）；以及根据已移除所述背景噪声的所述差分图像进行物体追踪（步骤S17）；其中，所述背景图像及所述差分图像可被储存于储存单元。Next, the following describes the detailed implementation of the operation method of the object tracking device according to the embodiment of the present invention, which includes the following steps: acquiring a background image when the image sensor is turned off relative to the light source (step S11 ); Obtain the operation image when it is on (step S12 ); use the processing unit to obtain the background information of the background image (step S13 ); use the processing unit to calculate the difference image between the operation image and the background image (step S14 ); use the processing unit to obtain object information of the differential image (step S15 ); compare the background information with the object information to remove background noise of the differential image (step S16 ); and performing object tracking according to the difference image from which the background noise has been removed (step S17 ); wherein, the background image and the difference image may be stored in a storage unit.
如图2至5D所示，图4显示本发明实施例1物体追踪装置的图像获取及光源点亮的示意图；图5A-5D显示本发明实施例1物体追踪装置的操作方法的示意图。As shown in FIGS. 2 to 5D , FIG. 4 shows a schematic diagram of image acquisition and light source lighting of the object tracking device according to Embodiment 1 of the present invention; FIGS. 5A-5D show schematic diagrams of the operation method of the object tracking device according to Embodiment 1 of the present invention.
本实施例中，所述光源11以一发光频率发光且所述图像传感器12以一取样频率依序获取图像。为了消除环境光源的影响，所述取样频率选择高于所述发光频率，以使所述图像传感器12可相对所述光源11点亮及熄灭时获取图像，例如相对所述光源11点亮时获取并输出操作图像Io（例如图4中以实线箭头表示者）且相对所述光源11熄灭时获取并输出背景图像Ib（例如图4中以虚线箭头表示者）。In this embodiment, the light source 11 emits light at a light emitting frequency and the image sensor 12 acquires images sequentially at a sampling frequency. In order to eliminate the influence of ambient light sources, the sampling frequency is selected to be higher than the luminous frequency, so that the image sensor 12 can acquire images when the light source 11 is on and off, for example, when the light source 11 is on And output the operation image Io (such as the one indicated by the solid arrow in FIG. 4 ) and obtain and output the background image Ib (such as the one indicated by the dotted arrow in FIG. 4 ) when the light source 11 is turned off.
步骤S11：所述图像传感器12相对所述光源11熄灭时获取并输出背景图像Ib（如图5A所示），其可先被储存于所述第一储存单元13中；其中，此处假设所述背景图像Ib仅包括背景物体20。Step S11 : when the image sensor 12 is turned off relative to the light source 11, it acquires and outputs a background image Ib (as shown in FIG. 5A ), which may first be stored in the first storage unit 13; wherein, it is assumed here that The background image Ib only includes background objects 20 .
步骤S12：所述图像传感器12接着相对所述光源11点亮时获取并输出操作图像Io（如图5B所示）；其中，此处假设所述操作图像Io包括所述背景物体20及物体30。由于所述图像传感器12是以顺序传输图像资料，所述操作图像Io则不需储存于所述第一储存单元13而直接被传送至所述处理单元14进行后处理。StepS12 : The image sensor 12 then acquires and outputs an operation image Io (as shown in FIG. 5B ) when it is turned on relative to the light source 11; wherein, it is assumed here that the operation image Io includes the background object 20 and the object 30. Since the image sensor 12 transmits image data sequentially, the operation image Io is directly sent to the processing unit 14 for post-processing without being stored in the first storage unit 13 .
步骤S13：所述处理单元14求出储存于所述第一储存单元13中所述背景图像Ib的背景信息并储存于所述第一储存单元13；其中，所述背景信息可为至少一背景物体位于所述背景图像Ib的背景物体位置。例如，所述处理单元14将所述背景图像Ib中亮度大于亮度阈值TH1（可事先储存于所述第一储存单元13）的象素区域识别为背景物体20，其具有背景物体位置21。所述背景物体位置21例如可为所述背景物体20的中心位置、重心位置、边缘位置或其他预设位置。必须说明的是，步骤S13可早于、晚于或与步骤S12同时进行。StepS13 : The processing unit 14 obtains the background information of the background image Ib stored in the first storage unit 13 and stores it in the first storage unit 13; wherein, the background information can be at least one The background object is located at the background object position of the background image Ib. For example, the processing unit 14 recognizes a pixel area in the background image Ib whose brightness is greater than a brightness threshold TH1 (which can be stored in the first storage unit 13 in advance) as a background object 20 , which has a background object position 21 . The background object position 21 can be, for example, the center position, center of gravity position, edge position or other preset positions of the background object 20 . It must be noted that stepS13 can be performed earlier, later than or simultaneously with stepS12 .
步骤S14：所述处理单元14接着计算所述操作图像Io与所述背景图像Ib的差分图像（Io-Ib）并储存于所述第一储存单元13。一种实施例中，所述差分图像（Io-Ib）优选复写（overwrite）于所述背景图像Ib在所述第一储存单元13中的储存空间，藉以降低所述第一储存单元13的记忆体容量，但并不以此为限。本实施例中，当所述背景物体20位置固定时，藉由计算所述差分图像（Io-Ib）则可完全消除所述背景物体20（如第5C图所示）而仅剩下所述物体30；然而，当所述背景物体20的位置随时间改变时，所述差分图像（Io-Ib）′中仍会包括一部分背景物体20′（如第5D图所示）；其中，所述部分背景物体20′的形状仅为例示性。Step S14 : the processing unit 14 then calculates the difference image (Io−Ib) of the operation image Io and the background image Ib and stores it in the first storage unit 13 . In one embodiment, the differential image (Io-Ib) is preferably overwritten in the storage space of the background image Ib in the first storage unit 13, so as to reduce the memory of the first storage unit 13 body capacity, but not limited thereto. In this embodiment, when the position of the background object 20 is fixed, the background object 20 (as shown in FIG. 5C ) can be completely eliminated by calculating the difference image (Io-Ib), leaving only the object 30; however, when the position of the background object 20 changes over time, the difference image (Io-Ib)' will still include a part of the background object 20' (as shown in Figure 5D); wherein, the The shape of part of the background object 20' is merely illustrative.
步骤S15：所述处理单元14求出所述第一储存单元13中所述差分图像（Io-Ib）′的物体信息并储存于所述第一储存单元13中；其中，所述物体信息可为至少一物体位于所述差分图像（Io-Ib）′的物体位置。例如，所述处理单元14将所述差分图像（Io-Ib）′中亮度大于亮度阈值TH2（可事先储存于所述第一储存单元13）的象素区域识别为物体，此时包括物体30及20′且分别具有物体位置31及21′，其中所述物体位置31及21′例如可分别为所述物体30及21′的中心位置、重心位置、边缘位置或其他预设位置。如前所述，若所述物体追踪装置另包括第二储存单元15储存预设背景图像，所述处理单元14于计算所述差分图像（Io-Ib）′前，先计算所述背景图像Ib与所述预设背景图像的差分背景图像以作为所述背景图像。Step S15 : The processing unit 14 obtains the object information of the difference image (Io-Ib)' in the first storage unit 13 and stores it in the first storage unit 13; wherein, the object information It may be an object position where at least one object is located in the differential image (Io-Ib)'. For example, the processing unit 14 recognizes the pixel area in the difference image (Io-Ib)' whose brightness is greater than the brightness threshold TH2 (which can be stored in the first storage unit 13 in advance) as an object, including the object 30 and 20' and have object positions 31 and 21' respectively, wherein the object positions 31 and 21' can be, for example, the center position, center of gravity position, edge position or other preset positions of the objects 30 and 21' respectively. As mentioned above, if the object tracking device further includes a second storage unit 15 to store a preset background image, the processing unit 14 first calculates the background image Ib before calculating the difference image (Io-Ib)′ A background image differing from the preset background image is used as the background image.
步骤S16：所述处理单元14接着比较所述背景信息与所述物体信息以移除背景噪声。本实施例中，当物体（例如20′）与所述背景信息相关，例如所述物体20′的所述物体位置（例如21′）距离所述背景物体位置（例如21）小于距离阈值且所述物体20′的大小小于尺寸阈值时，所述处理单元14将所述物体识别为与所述物体信息相关而属于背景噪声或无效物体而予以移除；其中，所述距离阈值及所述尺寸阈值均可事先储存于所述第一储存单元13中。Step S16 : The processing unit 14 then compares the background information with the object information to remove background noise. In this embodiment, when the object (such as 20') is related to the background information, for example, the object position (such as 21') of the object 20' is less than the distance threshold from the background object position (such as 21) and the When the size of the object 20' is smaller than the size threshold, the processing unit 14 identifies the object as related to the object information and belongs to background noise or an invalid object and removes it; wherein, the distance threshold and the size The threshold values can all be stored in the first storage unit 13 in advance.
步骤S17：所述处理单元14最后根据已移除所述背景噪声（或称无效物体）的所述差分图像进行物体追踪；也就是，所述处理单元14根据所述物体位置（例如31）距离所述背景物体位置（例如21）大于距离阈值的所述物体（例如30）进行物体追踪，由此消除移动背景噪声的干扰以提高物体追踪的正确性。本发明实施例中，当物体的物体位置距离所述背景物体位置大于距离阈值时则识别为所述手指图像。StepS17 : The processing unit 14 finally performs object tracking according to the difference image from which the background noise (or invalid object) has been removed; that is, the processing unit 14 performs object tracking according to the object position (for example, 31) The object (eg 30 ) whose distance from the background object position (eg 21 ) is greater than a distance threshold is subjected to object tracking, thereby eliminating the interference of moving background noise to improve the accuracy of object tracking. In the embodiment of the present invention, when the object position of the object is greater than a distance threshold from the background object position, it is identified as the finger image.
可以了解的是，图5A-5D中，所述背景物体20、无效物体20′及物体30的高度仅用以示意其亮度，以便与所述等亮度阈值TH1及TH2相比较。所述背景物体20、无效物体20′及物体30可具有不同亮度、面积、形状及位置等，并不限于第5A-5D图所示者。此外，所述等亮度阈值TH1及TH2可相同或不同。It can be understood that, in FIGS. 5A-5D , the heights of the background object 20 , the invalid object 20 ′ and the object 30 are only used to illustrate their brightness, so as to compare with the equal brightness thresholds TH1 and TH2 . The background object 20 , the invalid object 20 ′ and the object 30 may have different brightness, area, shape and position, etc., and are not limited to those shown in FIGS. 5A-5D . In addition, the isoluminance thresholds TH1 and TH2 may be the same or different.
综上所述，已知光学物体追踪装置由于无法完全消除移动背景光源的影响而仅适用于使用位置固定的装置。而本发明提出的一种物体追踪装置（图2）及其操作方法（图3），即使装设于交通工具或可携式电子装置等使用位置会改变的装置或设备上，仍可有效消除移动背景光源的影响以增加物体追踪的正确性。To sum up, the known optical object tracking devices are only suitable for fixed-position devices because they cannot completely eliminate the influence of moving background light sources. However, the object tracking device (Fig. 2) and its operation method (Fig. 3) proposed by the present invention can effectively eliminate the Moves the influence of background light sources to increase the accuracy of object tracking.
虽然本发明通过以前述实施例披露，但是其并非用以限定本发明，任何本发明所属技术领域中具有通常知识的技术人员，在不脱离本发明的精神和范围内，当可作各种的更动与修改。因此本发明的保护范围当视后附的申请专利范围所界定的范围为准。Although the present invention is disclosed by the aforementioned embodiments, it is not intended to limit the present invention. Any skilled person in the technical field to which the present invention belongs can make various modifications without departing from the spirit and scope of the present invention. Changes and Modifications. Therefore, the scope of protection of the present invention shall be as defined by the scope of the appended patent application.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210307139.1ACN103632340B (en) | 2012-08-24 | 2012-08-24 | Object tracking device and operation method thereof |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210307139.1ACN103632340B (en) | 2012-08-24 | 2012-08-24 | Object tracking device and operation method thereof |
| Publication Number | Publication Date |
|---|---|
| CN103632340A CN103632340A (en) | 2014-03-12 |
| CN103632340Btrue CN103632340B (en) | 2017-11-24 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210307139.1AActiveCN103632340B (en) | 2012-08-24 | 2012-08-24 | Object tracking device and operation method thereof |
| Country | Link |
|---|---|
| CN (1) | CN103632340B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11881018B2 (en) | 2018-07-10 | 2024-01-23 | Hangzhou Taro Positioning Technology Co., Ltd. | Detecting dual band infrared light source for object tracking |
| CN113992841B (en)* | 2021-09-27 | 2025-06-20 | 青岛小鸟看看科技有限公司 | Controller optical tracking method and system under strong outdoor light |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101617535A (en)* | 2007-03-28 | 2009-12-30 | 富士通株式会社 | Image processing apparatus, image processing method, image processing program |
| CN101916448A (en)* | 2010-08-09 | 2010-12-15 | 云南清眸科技有限公司 | Moving object detecting method based on Bayesian frame and LBP (Local Binary Pattern) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6349113B1 (en)* | 1997-11-03 | 2002-02-19 | At&T Corp. | Method for detecting moving cast shadows object segmentation |
| US6421462B1 (en)* | 1998-02-06 | 2002-07-16 | Compaq Computer Corporation | Technique for differencing an image |
| WO2005069197A1 (en)* | 2003-12-31 | 2005-07-28 | Lockheed Martin Missiles & Fire Control | A method and system for adaptive target detection |
| CN102568005B (en)* | 2011-12-28 | 2014-10-22 | 江苏大学 | Moving object detection method based on Gaussian mixture model |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101617535A (en)* | 2007-03-28 | 2009-12-30 | 富士通株式会社 | Image processing apparatus, image processing method, image processing program |
| CN101916448A (en)* | 2010-08-09 | 2010-12-15 | 云南清眸科技有限公司 | Moving object detecting method based on Bayesian frame and LBP (Local Binary Pattern) |
| Publication number | Publication date |
|---|---|
| CN103632340A (en) | 2014-03-12 |
| Publication | Publication Date | Title |
|---|---|---|
| CN104685318B (en) | Motion sensor device, circuit, recording medium, and image processing device | |
| US9542045B2 (en) | Detecting and tracking touch on an illuminated surface using a mean-subtracted image | |
| US9122917B2 (en) | Recognizing gestures captured by video | |
| CN104603574B (en) | Motion sensor device with multiple light sources | |
| CN104049792B (en) | Operation detection means and operation detection method | |
| TWI450154B (en) | Optical touch system and object detection method therefor | |
| US10255682B2 (en) | Image detection system using differences in illumination conditions | |
| KR20110123257A (en) | Clarify touch pointers with active display feedback | |
| US9888188B2 (en) | Image capture enhancement using dynamic control image | |
| US10348983B2 (en) | Non-transitory storage medium encoded with computer readable image processing program, information processing system, information processing apparatus, and image processing method for determining a position of a subject in an obtained infrared image | |
| KR20160108386A (en) | 3d silhouette sensing system | |
| CN109685032A (en) | Image processing method, device, electronic equipment and storage medium | |
| JP2010211617A (en) | Imaging apparatus, moving body detection method, moving body detection circuit and program | |
| JP6870474B2 (en) | Gaze detection computer program, gaze detection device and gaze detection method | |
| US9690430B2 (en) | Touch detection apparatus, touch detection method and recording medium | |
| TWI517092B (en) | Three-dimensional gesture sensing device and method of sensing three-dimensional gestures | |
| CN103632340B (en) | Object tracking device and operation method thereof | |
| TW201800901A (en) | Method for detecting motion information and photosensitive array | |
| TWI518639B (en) | Object tracking device and operating method thereof | |
| US20240377540A1 (en) | Power-efficient hand tracking with time-of-flight sensor | |
| CN103565399B (en) | Pupil detection device | |
| TWI597487B (en) | Method and system for touch point indentification and computer readable mediumassociatied therewith | |
| JP2007249743A (en) | Moving object identification method, moving object identification device, and program for executing moving object identification processing | |
| JP4611919B2 (en) | Pedestrian recognition device | |
| US9092063B2 (en) | Electronic system |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |