In space life science research，drosophila melanogaster （fruit fly） serves as a representative model organism for exploring the effects of microgravity environments on biological behavior，neural activity，and metabolism. Achieving precise and efficient multi-object tracking of drosophila is crucial to understanding their motion patterns and behavioral mechanisms. However，given their small body size，nonlinear motion，and high visual similarity among individuals，especially in dense scenes，existing multi-object tracking （MOT） methods face considerable challenges. To address this，we constructed a drosophila multi-object tracking dataset under ground-based experimental conditions，designed for space station applications. The dataset contains high-density video sequences with complex and dynamic behavior，providing valuable data support for intelligent behavior analysis of drosophila. In terms of methodology，existing MOTR-based approaches achieve end-to-end multi-object tracking but suffer from inherent limitations that lead to suboptimal detection performance. To overcome this issue，this study proposes a novel end-to-end multi-object tracking framework that effectively enhances detection accuracy and tracking robustness.

A ground-based simulated space environment dataset for multi-object tracking of drosophila was constructed on the basis of SpaceAnimal，comprising 20 video sequences （a total of 2 500 annotated frames） that capture high-density and high-dynamic motion characteristics. Moreover，we propose DN-MeMOTR，attempting to enhance the performance of detection by reconstructing ground truths with noises. Noised samples are generated from ground truth data by flipping the label and shifting the bounding box. We use label noise and box noise scales to control the scale of noise separately. Noised samples and initial learnable detect queries serve as detect queries and are concatenated with track queries，sequentially updated via self-attention and cross-attention. Furthermore，noised samples are employed solely during training and play no role in the inference stage. During inference，joint-filtering module is implemented to identify and remove targets that exhibit identical or similar characteristics across detect queries and track queries. Specifically，the ReID head outputs ReID features of detect and track queries. First，we filter out detect outputs whose scores are lower than the detection score threshold to obtain high score detection outputs indexes，then calculate the ReID similarity matrix and GIoU distance between detection outputs and track outputs. Two matrixes are linearly combined through a weighted sum.

We conduct experiments and analysis on drosophila dataset and compare the results with those of other prevalent MOT methods，such as ByteTrack，OC-SORT，and MeMOTR. MeMOTR demonstrates suboptimal detection performance compared with other detection-based tracking frameworks，which can be attributed to its inherent limitations. Our approach achieves the highest HOTA score of 71.8%，surpassing MeMOTR and Hybrid-SORT by 4.9% and 9.0%，respectively. With respect to the MOTA metric，our DN-MeMOTR obtains 87.6%，representing a substantial improvement of 19.3% over MeMOTR and 2.9% over Hybrid-SORT. We also obtain the highest DetA score of 73.4% and the highest IDF1 score of 84.9%. To enable a more direct comparison between DN-MeMOTR and the original MeMOTR，we conduct inference on video clips. According to the visualization results，MeMOTR tends to miss some targets，whereas DN-MeMOTR demonstrates better performance. The ablation study proves the effectiveness of denoising training and joint-filtering module.

We construct a multi-object tracking dataset of drosophila to simulate and support behavior analysis tasks under future space microgravity scenarios by extending the drosophila dataset of SpaceAnimal and propose DN-MeMOTR，which incorporates denoising training and joint-filtering modules. Denoising training aims to improve the network’s detection performance，overcoming the drawback of MOTR-like models. By contrast，ReID features and the joint-filtering module attempt to alleviate mismatching，boosting the performance of the original MeMOTR. Experiments show that our approach achieves superior performance on the drosophila dataset. The ablation study demonstrates the effectiveness of our components. It lays a solid foundation for the in-depth analysis of drosophila motion patterns and behavioral characteristics.