Search

In this paper, a novel YOLO-based detection model with deformable convolution network (DCN-YOLOv5) is developed, which is concerned with the object and key points detection and behavior tracking problem for Oplegnathus punctatus in the ammonia nitrogen environment. The proposed model can adapt to the posture change of the object by deforming the receptive field, which solves the problem of false and missed detection caused by the movement and occlusion. Moreover, a new multi-object multi-category tracking algorithm (MOMC-Tracking) is proposed to track and plot the trajectory and calculate the key behavioral characteristics parameters. In addition, an executable software which integrates the proposed DCN-YOLOv5 model and the MOMC-Tracking algorithm is proposed. Extensive experiments show that compared with the typical YOLO series of algorithms, the proposed model in this paper performs the best with the highest accuracy and the fastest convergence speed, where the mAP @0.5 and mAP @0.5:0.95 of the proposed DCN-YOLOv5 model are 93.71% and 57.45%, which are respectively improved by 1.78% and 24.77% as compared with those obtained by the original YOLOv5 model. [ABSTRACT FROM AUTHOR]

With the development of deep learning, the performance of many computer vision tasks has been greatly improved. For visual tracking, deep learning methods mainly focus on extracting better features or designing end-to-end trackers. However, during tracking specific targets most of the existing trackers based on deep learning are less discriminative and time-consuming. In this paper, a cascade based tracking algorithm is proposed to promote the robustness of the tracker and reduce time consumption. First, we propose a novel deep network for feature extraction. Since some pruning strategies are applied, the speed of the feature extraction stage can be more than 50 frames per second. Then, a cascade tracker named DCCT is presented to improve the performance and enhance the robustness by utilizing both texture and semantic features. Similar to the cascade classifier, the proposed DCCT tracker consists of several weaker trackers. Each weak tracker rejects some false candidates of the tracked object, and the final tracking results are obtained by synthesizing these weak trackers. Intensive experiments are conducted in some public datasets and the results have demonstrated the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]