Publications by authors named "Bao XiaoAn"
Article Synopsis
- A new wildlife target detection algorithm is introduced, based on the improved YOLOX-s network, aimed at enhancing detection accuracy in challenging rainy and nighttime conditions.
- The algorithm integrates three key components: the MobileViT-Pooling module for efficient feature extraction, the Dynamic Head module for improved task-specific detection, and the Focal-IoU module for better loss function handling.
- Experimental results show significant improvements in detection performance, with mAP scores increasing by 7.9% and 5.3%, demonstrating enhanced accuracy and reduced false detections for wildlife.
Object detector based on fully convolutional network achieves excellent performance. However, existing detection algorithms still face challenges such as low detection accuracy in dense scenes and issues with occlusion of dense targets. To address these two challenges, we propose an Global Remote Feature Modulation End-to-End (GRFME2E) detection algorithm.
View Article and Find Full Text PDFThe automatic generation of test cases oriented paths in an effective manner is a challenging problem for structural testing of software. The use of search-based optimization methods, such as genetic algorithms (GAs), has been proposed to handle this problem. This paper proposes an improved adaptive genetic algorithm (IAGA) for test cases generation by maintaining population diversity.
View Article and Find Full Text PDF