Concerning the problem that the surface defects of the coin are small, variable in shape, easily confused with the background and difficult to be detected, an improved algorithm of coin surface defect detection named DCA-YOLO (Deformable Convolution and Adaptive space feature fusion-YOLO) was proposed. First of all, due to the different shapes of defects, three network structures with deformable convolution modules added at different positions in the backbone network were designed, and the ability to extract defects was improved through convolution learning offset and adjusting parameters. Then, the adaptive spatial feature fusion network was used to learn the weight parameters to better adapt to targets with different scales by adjusting the contribution of each pixel in the feature maps of different scales. Finally, the anchor ratio was adjusted, the category weights were dynamically adjusted, the comparison network performance was optimized, thus, a model network to add deformable convolution before upsampling for multi-scale fusion of the output features of the backbone network was proposed. Experimental results show that on the coin defect dataset, the detection mAP (mean Average Precision) of DCA-YOLO algorithm reaches 92.8%, which is close to that of Faster-RCNN (Faster Region-based Convolutional Neural Network); compared with YOLOv3, the proposed algorithm has the detection speed basically the same with 3.3 percentage points improvement on detection mAP, and 3.2 percentage points increase on F1-score.
To improve the computational efficiency of stereo matching on foreground disparity estimation tasks, aiming at the disadvantage that the general networks use the complete binocular image as input and the input information redundancy is large due to the small proportion of the foreground space in the scene, a real-time target stereo matching algorithm based on sparse convolution was proposed. In order to realize and improve the sparse foreground disparity estimation of the algorithm, firstly, the sparse foreground mask and scene semantic features were obtained by the segmentation algorithm at the same time. Secondly, the sparse convolution was used to extract the spatial features of the foreground sparse region, and scene semantic features were fused with them. Then, the fused features were input into the decoding module for disparity regression. Finally, the foreground truth graph was used as the loss to generate the disparity graph. The test results on ApolloScape dataset show that the accuracy and real-time performance of the proposed algorithm are better than those of the state-of-the-art algorithms PSMNet (Pyramid Stereo Matching Network) and GANet (Guided Aggregation Network), and the single run time of the algorithm is as low as 60.5 ms. In addition, the proposed algorithm has certain robustness to the foreground occlusion, and can be used for the real-time depth estimation of targets.
A distributed strategy based on Stackelberg game was proposed to allocate cooperative power for cooperative networks. A Stackelberg game model was built at first, and the source node decided the price according to the cooperative power. Considering the relay's available resources, channel state, location and the price determined by source node, the relay node allocated the cooperative power to construct a user utility function. Then, the utility function was demonstrated to satisfy the conditions of concave function to ensure the existence of equilibrium. Subsequently, each node maximized its utility by finding the Stackelberg Equilibrium (SE) of optimum power and price. Finally, the simulation results proved the existence of equilibrium point, and the node's price, cooperative power and each node's utility were analyzed when the source node was in a different position. In the experiments, the cooperative power and price of the closer user respectively were 1.29 times and 1.37 times of the farther user. The experimental results show that the proposed strategy is effective, and it can be used in cooperative network and some other distributed networks.