技术领域technical field
本发明属于箱包领域，尤其涉及一种基于步态识别算法的智能跟随旅行箱。The invention belongs to the field of bags, in particular to an intelligent following suitcase based on a gait recognition algorithm.
背景技术Background technique
旅行箱是箱包中的一类，它包括箱包体、伸缩拉杆和箱包底轮，因其使用方便而受到广泛应用。旅行箱有着漫长的历史，如今旅行箱携带物品过重，使用者携带不便，在携带旅行箱走动过程中无疑加重了负担。随着科学技术的飞速发展，旅行箱也得到了技术改进。现有的使用激光、RFID等技术基本实现了旅行箱的自动跟随功能，但其具有诸多缺点，例如，基于激光技术的旅行箱无法在恶劣天气下(如下雨、下雪、下冰雹等)使用，在雨天，由于激光信号在雨中的传输衰减特性，无法正常识别人与旅行箱的距离，在雪天、冰雹天，激光错误的将雪、冰雹等障碍物识别为人体，过早发生反射信号，造成识别错误；基于RFID技术的旅行箱需要使用者时刻佩戴RFID接收器，并且只要任何拥有该接收器的人都能使旅行箱自由跟随，这对使用者来说是十分不便利并且危险的。Suitcase is a class of luggage, which includes a luggage body, a telescopic pull rod and a luggage bottom wheel, and is widely used because of its ease of use. Suitcases have a long history. Nowadays, suitcases are too heavy to carry, and it is inconvenient for users to carry them. It will undoubtedly increase the burden when carrying suitcases for walking. With the rapid development of science and technology, suitcases have also been technologically improved. Existing technologies such as laser and RFID have basically realized the automatic following function of suitcases, but they have many disadvantages. For example, suitcases based on laser technology cannot be used in bad weather (such as rain, snow, hail, etc.) In rainy days, due to the transmission attenuation characteristics of laser signals in rain, the distance between people and suitcases cannot be recognized normally. In snowy and hail days, the laser mistakenly recognizes obstacles such as snow and hail as human bodies, and the reflected signal occurs prematurely. , causing identification errors; the suitcase based on RFID technology requires the user to wear the RFID receiver at all times, and as long as anyone who has the receiver can make the suitcase follow freely, this is very inconvenient and dangerous for the user .
现有旅行箱所使用的跟随技术主要是以上所说的两种技术，其智能性差，识别准确率低，显然已无法满足人们的需求，人们渴求一种更加便利、安全的旅行箱。The following technology used in the existing suitcase is mainly the above-mentioned two technologies, which have poor intelligence and low recognition accuracy, and obviously cannot meet people's needs. People are longing for a more convenient and safe suitcase.
发明内容Contents of the invention
发明目的：本发明目的是提供一种基于步态识别算法的智能跟随旅行箱，以解决现有技术智能性差、识别准确率低的问题。Purpose of the invention: The purpose of the invention is to provide a smart following suitcase based on a gait recognition algorithm to solve the problems of poor intelligence and low recognition accuracy in the prior art.
技术方案：本发明包括箱体，所述的箱体正面设有摄像头与微处理器，所述的摄像头与微处理器通过电线与锂电池连接，所述的锂电池固定于箱体内部，所述箱体的底部设有万向轮，箱体的外侧设有电源控制面板。Technical solution: the present invention includes a box, the front of the box is provided with a camera and a microprocessor, the camera and the microprocessor are connected to a lithium battery through wires, and the lithium battery is fixed inside the box. The bottom of the box is provided with universal wheels, and the outside of the box is provided with a power control panel.
所述的电源控制面板包括电源开关、电量显示口、电源充电口与模式选择。The power control panel includes a power switch, a power display port, a power charging port and mode selection.
所述的电源开关与电机连接，用于开关电机。The power switch is connected with the motor and used for switching the motor.
所述的电源充电口上设有防水防尘塞，用于防水防尘。The charging port of the power supply is provided with a waterproof and dustproof plug for waterproof and dustproof.
所述的模式选择包括学习模式与跟随模式。The mode selection includes learning mode and following mode.
所述跟随模式的默认跟随间距为50—100cm。The default follow distance of the follow mode is 50-100cm.
所述的万向轮通过电机与锂电池连接。Described universal wheel is connected with lithium battery through motor.
所述的万向轮采用高性能的聚氨酯材料，防止轮子磨损。Described universal wheel adopts high-performance polyurethane material, prevents wheel from wearing and tearing.
有益效果：本发明采用步态识别技术，通过人们走路的步态进行身份识别，具有精度高、安全便利、不易伪装、适用范围广等优点，十分适合运用于箱包领域，且在箱包领域具有巨大的市场空间，本发明的旅行箱解放了使用者的双手，解决了现有技术智能性差、识别准确率低的问题，使用者不必再为旅行箱丢失而烦恼。Beneficial effects: the present invention adopts gait recognition technology to carry out identity recognition through people's walking gait, which has the advantages of high precision, safety and convenience, not easy to camouflage, wide application range, etc. market space, the suitcase of the present invention liberates the user's hands, solves the problems of poor intelligence and low recognition accuracy in the prior art, and the user no longer has to worry about losing the suitcase.
附图说明Description of drawings
图1为本发明的整体结构示意图；Fig. 1 is the overall structure schematic diagram of the present invention;
图2为本发明的电源控制面板示意图；Fig. 2 is a schematic diagram of a power control panel of the present invention;
图3为本发明的工作流程图。Fig. 3 is a working flow diagram of the present invention.
具体实施方式Detailed ways
下面结合附图对本发明作进一步说明。The present invention will be further described below in conjunction with accompanying drawing.
如图1和图2所示，本发明包括箱体1、锂电池2、摄像头3、微型处理器4、万向轮5、电源开关6、电量显示口7、电源充电口8与模式选择9。箱体1为产品主体，承载其他各个功能组块；锂电池2封装固定在旅行箱内部的底部，为整个系统供电；摄像头3和微型处理器4安装在箱体1的正面，通过电线与锂电池2相连；万向轮5安装在箱体1的底部，通过电机与锂电池2相连，万向轮5采用高性能的聚氨酯材料，防止轮子磨损；箱体1的外侧设有电源控制面板，电源控制面板包括电源开关6、电量显示口7、电源充电口8与模式选择9，电源开关6与电机连接，用于开关电机，电源充电口8上设有防水防尘塞，用于防水防尘，模式选择9包括学习模式与跟随模式，跟随模式的默认跟随间距为50—100cm，电量显示口7采用5枚LED灯，实现剩余电量的显示。As shown in Figures 1 and 2, the present invention includes a box body 1, a lithium battery 2, a camera 3, a microprocessor 4, a universal wheel 5, a power switch 6, a power display port 7, a power charging port 8 and a mode selection 9 . Box 1 is the main body of the product, carrying other functional blocks; Lithium battery 2 is packaged and fixed at the bottom of the suitcase to supply power for the whole system; The battery 2 is connected; the universal wheel 5 is installed at the bottom of the box body 1, and is connected with the lithium battery 2 through the motor. The universal wheel 5 is made of high-performance polyurethane material to prevent wheel wear; the outer side of the box body 1 is provided with a power control panel, The power control panel includes a power switch 6, a power display port 7, a power charging port 8 and a mode selection 9. The power switch 6 is connected to the motor for switching the motor. The power charging port 8 is provided with a waterproof and dustproof plug for waterproof and waterproof Dust, mode selection 9 includes learning mode and follow mode, the default follow distance of follow mode is 50-100cm, and the power display port 7 uses 5 LED lights to realize the display of remaining power.
如图3所示，在初次使用时，如果使用者想要使用跟随功能，首先必须打开旅行箱开关，选择学习模式，由摄像头3采集人的体型、走路姿态等步态特征，通过检测与跟踪获得步态的视频序列，经过预处理分析提取被识别者的步态特征。即对图像序列中的步态运动进行运动检测、运动分割、特征提取等步态识别前期的关键处理。As shown in Figure 3, when using for the first time, if the user wants to use the following function, he must first turn on the switch of the suitcase, select the learning mode, and the camera 3 collects the gait characteristics such as the body shape and walking posture of the person, and through detection and tracking The gait video sequence is obtained, and the gait features of the recognized person are extracted through preprocessing analysis. That is, the key processing in the early stage of gait recognition, such as motion detection, motion segmentation, and feature extraction, is performed on the gait motion in the image sequence.
然后，将获取的特征传入卷积神经网络(CNN)等多重神经网络结构进行学习，将结果保存为模型存入数据库。Then, the acquired features are passed into multiple neural network structures such as convolutional neural network (CNN) for learning, and the results are saved as models and stored in the database.
最后，使用者选择跟随模式，此时旅行箱调用已存储模型，将其与被识别者进行比对，当比对结果超过某一阈值时确认该被识别者为模型存储者，即开始跟随，默认跟随间距为50—100厘米。同时，在跟随的过程中，如果发现旅行箱跟随效果不理想，使用者可以再次开启学习模式，此时模型会继续学习摄像头3所传入的更多的画面，从而分析出更加多元的特征并学习，反复完善模型并存储至数据库中。Finally, the user selects the follow mode. At this time, the suitcase invokes the stored model and compares it with the recognized person. When the comparison result exceeds a certain threshold, it is confirmed that the recognized person is the model storer, and it starts to follow. The default follow distance is 50-100 cm. At the same time, in the process of following, if the following effect of the suitcase is found to be unsatisfactory, the user can turn on the learning mode again. At this time, the model will continue to learn more images from the camera 3, thereby analyzing more diverse features and Learn, improve the model repeatedly and store it in the database.
本发明的旅行箱支持保存多人的步态信息模型，才用1：K方式进行匹配识别，只要使用者是所保存模型中的一个人即可The suitcase of the present invention supports the preservation of the gait information models of multiple people, and only uses the 1:K method for matching and identification, as long as the user is one of the saved models.
在以后的使用中无需进行上述的学习模式，可以直接选择跟随模式，即可开启跟随功能。如果想要旅行箱跟随其他使用者，此时可视作初次使用(对该使用者而言是初次使用，而非对旅行箱而言)，重复上述流程即可。In future use, there is no need to perform the above learning mode, you can directly select the follow mode to enable the follow function. If you want the suitcase to follow other users, it can be regarded as the first use at this time (it is the first use for the user, not for the suitcase), and the above process can be repeated.
以上显示和描述了本发明的基本原理、主要特征和本发明的优点,对于本领域技术人员而言，显然本发明不限于上述示范性实施例的细节，而且在不背离本发明的精神或基本特征的情况下，能够以其他的具体形式实现本发明。因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本发明的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化囊括在本发明内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。The basic principles, main features and advantages of the present invention have been shown and described above. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and without departing from the spirit or fundamentals of the present invention. The present invention can be implemented in other specific forms without any specific features. Accordingly, the embodiments should be regarded in all points of view as exemplary and not restrictive, the scope of the invention being defined by the appended claims rather than the foregoing description, and it is therefore intended that the scope of the invention be defined by the appended claims rather than by the foregoing description. All changes within the meaning and range of equivalents of the elements are embraced in the present invention. Any reference sign in a claim should not be construed as limiting the claim concerned.
此外，应当理解，虽然本说明书按照实施方式加以描述，但并非每个实施方式仅包含一个独立的技术方案，说明书的这种叙述方式仅仅是为清楚起见，本领域技术人员应当将说明书作为一个整体，各实施例中的技术方案也可以经适当组合，形成本领域技术人员可以理解的其他实施方式。In addition, it should be understood that although this specification is described according to implementation modes, not each implementation mode only contains an independent technical solution, and this description in the specification is only for clarity, and those skilled in the art should take the specification as a whole , the technical solutions in the various embodiments can also be properly combined to form other implementations that can be understood by those skilled in the art.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810666281.2ACN108813863A (en) | 2018-06-22 | 2018-06-22 | A kind of intelligence based on Algorithm for gait recognition follows suitcase |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810666281.2ACN108813863A (en) | 2018-06-22 | 2018-06-22 | A kind of intelligence based on Algorithm for gait recognition follows suitcase |
| Publication Number | Publication Date |
|---|---|
| CN108813863Atrue CN108813863A (en) | 2018-11-16 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810666281.2APendingCN108813863A (en) | 2018-06-22 | 2018-06-22 | A kind of intelligence based on Algorithm for gait recognition follows suitcase |
| Country | Link |
|---|---|
| CN (1) | CN108813863A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105455365A (en)* | 2015-11-19 | 2016-04-06 | 宁波江东士兰微电子科技有限公司 | Intelligent suitcase |
| CN105843226A (en)* | 2016-04-06 | 2016-08-10 | 柳州定店科技有限公司 | Multi-image following method for intelligent luggage case |
| CN106127117A (en)* | 2016-06-16 | 2016-11-16 | 哈尔滨工程大学 | Based on binocular vision quick high robust identification, location automatically follow luggage case |
| CN106182024A (en)* | 2016-07-11 | 2016-12-07 | 天津艾思科尔科技有限公司 | A kind of available image carries out the household service robot of gait detection |
| CN107811375A (en)* | 2017-11-10 | 2018-03-20 | 左国刚 | From following luggage case and its follower method |
| CN107951147A (en)* | 2017-12-15 | 2018-04-24 | 芜湖酷哇机器人产业技术研究院有限公司 | Automatic trailing type suitcase |
| CN207370256U (en)* | 2017-06-12 | 2018-05-18 | 灵动科技（北京）有限公司 | Luggage case, smart machine and the system of automatically walk |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105455365A (en)* | 2015-11-19 | 2016-04-06 | 宁波江东士兰微电子科技有限公司 | Intelligent suitcase |
| CN105843226A (en)* | 2016-04-06 | 2016-08-10 | 柳州定店科技有限公司 | Multi-image following method for intelligent luggage case |
| CN106127117A (en)* | 2016-06-16 | 2016-11-16 | 哈尔滨工程大学 | Based on binocular vision quick high robust identification, location automatically follow luggage case |
| CN106182024A (en)* | 2016-07-11 | 2016-12-07 | 天津艾思科尔科技有限公司 | A kind of available image carries out the household service robot of gait detection |
| CN207370256U (en)* | 2017-06-12 | 2018-05-18 | 灵动科技（北京）有限公司 | Luggage case, smart machine and the system of automatically walk |
| CN107811375A (en)* | 2017-11-10 | 2018-03-20 | 左国刚 | From following luggage case and its follower method |
| CN107951147A (en)* | 2017-12-15 | 2018-04-24 | 芜湖酷哇机器人产业技术研究院有限公司 | Automatic trailing type suitcase |
| Publication | Publication Date | Title |
|---|---|---|
| CN106127117B (en) | Automatically following suitcases based on binocular vision fast and robust recognition and localization | |
| Jensen et al. | Evaluating state-of-the-art object detector on challenging traffic light data | |
| Ronao et al. | Human activity recognition using smartphone sensors with two-stage continuous hidden Markov models | |
| Kawewong et al. | Online and incremental appearance-based SLAM in highly dynamic environments | |
| Moradi et al. | Compare of machine learning and deep learning approaches for human activity recognition | |
| CN202196458U (en) | Face recognition system | |
| CN103390168A (en) | Intelligent wheelchair dynamic gesture recognition method based on Kinect depth information | |
| CN105717927A (en) | Bearing device and control method used for bearing device | |
| Douillard et al. | Laser and Vision Based Outdoor Object Mapping. | |
| Hadsell et al. | Online learning for offroad robots: Using spatial label propagation to learn long-range traversability | |
| Tian et al. | Pruning-based YOLOv4 algorithm for underwater gabage detection | |
| CN108835809A (en) | A kind of intelligence based on ROS follows luggage case and its control method | |
| Batool et al. | Telemonitoring of daily activities based on multi-sensors data fusion | |
| CN105852358A (en) | RFID space signal based intelligent following luggage box | |
| Glandon et al. | 3d skeleton estimation and human identity recognition using lidar full motion video | |
| CN108813863A (en) | A kind of intelligence based on Algorithm for gait recognition follows suitcase | |
| CN106184330A (en) | A kind of multifunctional intellectual follows stroller | |
| Tongprasit et al. | PIRF-Nav 2: Speeded-up online and incremental appearance-based SLAM in an indoor environment | |
| CN212061388U (en) | Intelligent follow suitcase based on UWB communication | |
| CN105550642A (en) | Gender identification method and system based on multi-scale linear difference characteristic low-rank expression | |
| CN108937026A (en) | A kind of automatic obstacle-avoiding suitcase based on binocular vision | |
| CN207898100U (en) | A kind of Intelligent luggage carrier | |
| CN205507544U (en) | Bering device | |
| CN103767294A (en) | Multifunctional luggage box | |
| CN117037266A (en) | Control method, device and system for trunk of vehicle and storage medium |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20181116 |