Online multiple pedestrians tracking using deep temporal appearance matching association

Inference-Domain Network Evolution: A New Perspective for One-Shot Multi-Object Tracking

The supervised one-shot multi-object tracking (MOT) algorithms have achieved satisfactory performance benefiting from a large amount of labeled data. However, in real applications, acquiring plenty of laborious manual annotations is not practical. It is necessary to adapt the one-shot MOT model trained on a labeled domain to an unlabeled domain, yet such domain adaptation is a challenging problem. The main reason is that it has to detect and associate multiple moving objects distributed in various spatial locations, but there are obvious discrepancies in style, object identity, quantity, and scale among different domains. Motivated by this, we propose a novel inference-domain network evolution to enhance the generalization ability of the one-shot MOT model. Specifically, we design a spatial topology-based one-shot network (STONet) to perform the one-shot MOT task, where a self-supervision mechanism is employed to stimulate the feature extractor to learn the spatial contexts without any annotated information. Furthermore, a temporal identity aggregation (TIA) module is proposed to assist STONet to weaken the adverse effects of noisy labels in the network evolution. This designed TIA aggregates historical embeddings with the same identity to learn cleaner and more reliable pseudo labels. In the inference domain, the proposed STONet with TIA performs pseudo label collection and parameter update progressively to realize the network evolution from the labeled source domain to an unlabeled inference domain. Extensive experiments and ablation studies conducted on MOT15, MOT17, and MOT20, demonstrate the effectiveness of our proposed model.

Improving Multiple Pedestrian Tracking in Crowded Scenes with Hierarchical Association

Recently, advances in detection and re-identification techniques have significantly boosted tracking-by-detection-based multi-pedestrian tracking (MPT) methods and made MPT a great success in most easy scenes. Several very recent works point out that the two-step scheme of first detection and then tracking is problematic and propose using the bounding box regression head of an object detector to realize data association. In this tracking-by-regression paradigm, the regressor directly predicts each pedestrian's location in the current frame according to its previous position. However, when the scene is crowded and pedestrians are close to each other, the small and partially occluded targets are easily missed. In this paper, we follow this pattern and design a hierarchical association strategy to obtain better performance in crowded scenes. To be specific, at the first association, the regressor is used to estimate the positions of obvious pedestrians. At the second association, we employ a history-aware mask to filter out the already occupied regions implicitly and look carefully at the remaining regions to find out the ignored pedestrians during the first association. We integrate the hierarchical association in a learning framework and directly infer the occluded and small pedestrians in an end-to-end way. We conduct extensive pedestrian tracking experiments on three public pedestrian tracking benchmarks from less crowded to crowded scenes, demonstrating the proposed strategy's effectiveness in crowded scenes.

Human-computer interaction based health diagnostics using ResNet34 for tongue image classification

BACKGROUND AND OBJECTIVE

Tongue diagnosis is one of the characteristics of traditional Chinese medicine (TCM), but traditional tongue diagnosis is affected by many factors, and its differential diagnosis results are not widely recognized. The appearance of tongue diagnosis instruments is the product of the modernization of tongue diagnosis, and it has standard and objective advantages in clinical practice. In this study, based on standard tongue images, a tongue image dataset and detection model were constructed. And based on the deep learning convolutional neural network (CNN) algorithm and visual question answering technology, a human-computer interaction intelligent health detector for tongue image recognition is constructed.

METHODS

In this research, 1420 tongue images were collected. After screening, experts judged them, and annotated the tongue images to form tongue image datasets. Then the artificial intelligence network framework based on deep learning convolutional neural network (CNN), that is, ResNet34, is applied to this dataset to automatically extract image features and realize tongue images classification. Finally, the VGG16 network framework is applied to the dataset to compare the classification model and compare with the classification effect.

RESULTS

In this paper, relevant datasets were formed by collating the tongue images collected by annotation, which verified that the ResNet34 architecture could better perform the task of tooth mark and tongue feature recognition. Compared with similar learning tasks in existing studies, the accuracy of the teeth-printed tongue recognition model proposed in this study is more than 10% higher, which indicates that the CNN algorithm can distinguish teeth-printed tongue more accurately and effectively. At the same time, using datasets and models combined with visual question and answer technology, an AI health detector for TCM tongue image identification is designed, which can make health assessments and give suggestions to users.

CONCLUSION

This study adopts a convolutional neural network model based on deep learning, which can reduce the extraction of tongue features more quickly and conveniently. At the same time, the model architecture has excellent performance and strong generalization ability and is more accurate in judging users' health status.

Multiple Object Tracking in Deep Learning Approaches: A Survey

Object tracking is a fundamental computer vision problem that refers to a set of methods proposed to precisely track the motion trajectory of an object in a video. Multiple Object Tracking (MOT) is a subclass of object tracking that has received growing interest due to its academic and commercial potential. Although numerous methods have been introduced to cope with this problem, many challenges remain to be solved, such as severe object occlusion and abrupt appearance changes. This paper focuses on giving a thorough review of the evolution of MOT in recent decades, investigating the recent advances in MOT, and showing some potential directions for future work. The primary contributions include: (1) a detailed description of the MOT’s main problems and solutions, (2) a categorization of the previous MOT algorithms into 12 approaches and discussion of the main procedures for each category, (3) a review of the benchmark datasets and standard evaluation methods for evaluating the MOT, (4) a discussion of various MOT challenges and solutions by analyzing the related references, and (5) a summary of the latest MOT technologies and recent MOT trends using the mentioned MOT categories.