An efficient multi-task convolutional neural network for dairy farm object detection and segmentation

Abstract

Real-time and accurate detection of multiple types of targets and obstacles in dairy barns is a necessary function for autonomous pushing robots. To improve the efficiency of target recognition and to reduce the path extraction error of the pushing robot, on the basis of the high accuracy perception of every pixel collected with an embedded AI computer, a multi-task learning based dairy barn multi-type target recognition model Ghost CBAM Segmentation-Multi-task (GCS-MUL) was proposed, which could recognize dairy cows, obstacles and road targets in real-time and efficiently. Firstly, in order to enhance the ability to extract key features from the targets, the proposed model intergrades the Convolutional Block Attention Module (CBAM), a self-designed light-weight target feature extraction network Ghost CBAM Network (GCNet) as the backbone of the whole model. Secondly, to improve the model multi-scale feature fusion, Path Aggregation Network (PAN) and Feature Pyramid Network (FPN) structures with the GhostConv module were used in neck net. Finally, for real-time semantic segmentation dairy farms multiple targets, a Segmentation Head (Seg Head), which is composed of the Receptive Field Block (RFB), Pyramid Pooling Module (PPM) and Feature Fusion Module (FFM), was introduced. Experimental results showed that the mAP@0.5 (mean average precision IoU = 0.5) of the dairy farm target reached 94.86%. Compared to the YOLOv5 model, the precision and recall was improved by 7.47% and 6.85%, respectively. In comparison to the YOLOv7 model, the precision was improved by 5.1%. Furthermore, when compared to the SSD model, the proposed model have reduced the number of model parameters by 92.43%, and its average detection time was reduced by 84.37 ms, which is ideal for meeting the real-time target recognition requirements. The average detection time of the model is 66.43 ms, making it more suitable for deployment in embedded devices. Compared with Ghost CBAM-Detection (GC-Detect) without the introduction of the Seg Head, the precision, recall and mAP@0.5 was improved by 4.49%, 4.92% and 6.58%, respectively. The research results can provide accurate algorithms for real-time and efficient identification of dairy farm targets for pushing robots, and provide more effective road and environmental scene segmentation methods for autonomous walking.