Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation

Although the single-domain person re-identification (Re-ID) method has achieved great accuracy, the dependence on the label in the same image domain severely limits the scalability of this method. Therefore, cross-domain Re-ID has received more and more attention. In this paper, a novel cross-domain Re-ID method combining supervised and unsupervised learning is proposed, which includes two models: a triple-condition generative adversarial network (TC-GAN) and a dual-task feature extraction network (DFE-Net). We first use TC-GAN to generate labeled images with the target style, and then we combine supervised and unsupervised learning to optimize DFE-Net. Specifically, we use labeled generated data for supervised learning. In addition, we mine effective information in the target data from two perspectives for unsupervised learning. To effectively combine the two types of learning, we design a dynamic weighting function to dynamically adjust the weights of these two approaches. To verify the validity of TC-GAN, DFE-Net, and the dynamic weight function, we conduct multiple experiments on Market-1501 and DukeMTMC-reID. The experimental results show that the dynamic weight function can improve the performance of the models, and our method is better than many state-of-the-art methods.

Cross-domain person re-identification by hybrid supervised and unsupervised learning

We performed an electronic database search of published works from 2012 to mid-2021 that focus on human gait studies and apply machine learning techniques. We identified six key applications of machine learning using gait data: 1) Gait analysis where analyzing techniques and certain biomechanical analysis factors are improved by utilizing artificial intelligence algorithms, 2) Health and Wellness, with applications in gait monitoring for abnormal gait detection, recognition of human activities, fall detection and sports performance, 3) Human Pose Tracking using one-person or multi-person tracking and localization systems such as OpenPose, Simultaneous Localization and Mapping (SLAM), etc., 4) Gait-based biometrics with applications in person identification, authentication, and re-identification as well as gender and age recognition 5) “Smart gait” applications ranging from smart socks, shoes, and other wearables to smart homes and smart retail stores that incorporate continuous monitoring and control systems and 6) Animation that reconstructs human motion utilizing gait data, simulation and machine learning techniques. Our goal is to provide a single broad-based survey of the applications of machine learning technology in gait analysis and identify future areas of potential study and growth. We discuss the machine learning techniques that have been used with a focus on the tasks they perform, the problems they attempt to solve, and the trade-offs they navigate.

/pdf/a-survey-of-human-gait-based-artificial-intelligence-qixiou8c.pdf

A Survey of Human Gait-Based Artificial Intelligence Applications

LABNet: Local graph aggregation network with class balanced loss for vehicle re-identification

A comprehensive survey on person re-identification approaches: various aspects

PrGCN: Probability prediction with graph convolutional network for person re-identification

The invention discloses a ternary tree traversal-based lane line detection method and relates to the field of image processing. According to the method, candidate feature points which represent the center line of a lane line are extracted, and the number of pixel points required to be processed is reduced. The calculation efficiency of the algorithm is improved. The feature points of lane lines and noises are analyzed, and a method for filtering pseudo feature points irrelevant to the parameter space is provided. In this way, the parameter space conversion and the complex mathematical operation are avoided. The accuracy of lane line detection is improved. Meanwhile, a lane line prediction model is provided for carrying out lane line prediction in special road conditions. The internal memory is stored in the model. According to the change tendency of an image sequence from the past to the current, a lane line in a special road condition can be predicted. The lane line is predicted properly and reasonably. The accuracy of the detection result is improved.

Xiao Zhenzhen

Papers

PrGCN: Probability prediction with graph convolutional network for person re-identification

Ternary tree traversal-based lane line detection method