Cui Wang

Tracking specific targets, such as pedestrians and vehicles, has been the focus of recent vision-based multitarget tracking studies. However, in some real-world scenarios, unseen categories often challenge existing methods due to low-confidence detections, weak motion and appearance constraints, and long-term occlusions. To address these issues, this article proposes a tracklet-enhanced tracker called Multi-Tracklet Tracking (MTT) that integrates flexible tracklet generation into a multi-tracklet association framework. This framework first adaptively clusters the detection results according to their short-term spatio-temporal correlation into robust tracklets and then estimates the best tracklet partitions using multiple clues, such as location and appearance over time to mitigate error propagation in long-term association. Finally, extensive experiments on the benchmark for generic multiple object tracking demonstrate the competitiveness of the proposed framework.

In autonomous driving and robotics, 3D object detection using LiDAR point clouds is a critical task. However, existing single-frame 3D object detection methods face challenges such as noise, occlusions, and sparsity, which degrade detection performance. To address these, we propose the Sparse Temporal Fusion Network (STFNet), which leverages multi-frame historical information to improve 3D object detection accuracy. The contribution of STFNet contains three core modules: Multi-History Feature Alignment Module (MFAM), Sparse Feature Extraction Module (SFEM), and Temporal Fusion Transformer (TFformer). (1) MFAM: Ego-motion is used for compensation to align frames, establishing correlations between adjacent frames along the temporal dimension. (2) SFEM: Sparse extraction is performed on features from different time steps to obtain key features within the time series. (3) TFformer: The advanced temporal fusion attention mechanism is introduced to facilitate deep interactions between the current and historical frames. We validated the effectiveness of STFNet on the nuScenes dataset, achieving 71.8% NDS and 67.0% mAP. Compared to the benchmark method, our method improves 1.6% NDS and 1.5% mAP. Extensive experiments demonstrate that STFNet significantly outperforms most existing methods, highlighting the superiority and generalizability of our approach.

Zebrafish behavioral patterns reveal valuable insights for biomedical research. To accurately identify these patterns, visual tracking systems need to reconstruct 3D trajectories from multi-view video sequences. However, 3D zebrafish tracking faces challenges such as the dynamics in movements, the similarity in appearances, and the distortion caused by different viewpoints. In this paper, we propose a new method for robust 3D zebrafish trajectory reconstruction based on multi-view data fusion and global association. Our method generates reliable segments of 2D/3D trajectories, called tracklets , where we considering short-term cues of appearance similarity and motion consistency and proposing corresponding scoring metrics. Moreover, we use a lazy-reconstruction strategy to enhance the overall accuracy of 3D trajectories by taking into account the global context. Extensive experiments on the public 3D-ZeF20 dataset demonstrate the effectiveness of the proposed method, achieving 67.9% MOTA, 64.3% IDF1, and 55.0 MTBFm.

The problem of vehicle re-identification in surveillance scenarios has grown in popularity as a research topic. Deep learning has been successfully applied in re-identification tasks in the last few years due to its superior performance. However, deep learning approaches require a large volume of training data, and it is particularly crucial in vehicle re-identification tasks to have a sufficient amount of varying image samples for each vehicle. To collect and construct such a large and diverse dataset from natural environments is labor intensive. We offer a novel image sample synthesis framework to automatically generate new variants of training data by augmentation. First, we use an attention module to locate a local salient projection region in an image sample. Then, a lightweight convolutional neural network, the parameter agent network, is responsible for generating further image transformation states. Finally, an adversarial module is employed to ensure that the images in the dataset are distorted, while retaining their structural identities. This adversarial module helps to generate more appropriate and difficult training samples for vehicle re-identification. Moreover, we select the most difficult sample and update the parameter agent network accordingly to improve the performance. Our method draws on the adversarial networks strategy and the self-attention mechanism, which can dynamically decide the region selection and transformation degree of the synthesis images. Extensive experiments on the VeRi-776, VehicleID, and VERI-Wild datasets achieve good performance. Specifically, our method outperforms the state-of-the-art in MAP accuracy on VeRi-776 by 2.15%. Moreover, on VERI-Wil, a significant improvement of 7.15% is achieved.