1 November 2023 in Journal of Electronic Imaging
Aiming at the detection difficulties in camouflage target detection, such as the high similarity between the target and its background, serious damage to the edge, and strong concealment of the target, a camouflage target detection algorithm YOLO of camouflage object detection based on strong semantic information and feature fusion is proposed. First, the attention mechanism convolutional block attention module (CBAM) is constructed to highlight the important channel features and target spatial locations to further aggregate rich semantic information from the high-level feature map. Then the atrous spatial pyramid pooling module is constructed to repeatedly sample the multiscale feature maps to expand the receptive field of the neural network, reduce feature sparsity in the process of convolution, and ensure dense features and multiscale contextual semantic information enter the feature fusion module. Finally, the attention skip-connections are constructed based on the CBAM module for fusing the original feature maps extracted by the backbone network to the corresponding detection outputs so as to eliminate the redundant features as well as enrich the target information of the network outputs. In order to fully verify the performance of the proposed algorithm, a camouflage target detection dataset named strong camouflage efficiency target dataset (SCETD) is constructed. Experimental results on SCETD show that the precision and recall of the proposed algorithm achieve 96.1% and 87.1%, respectively. The AP0.5 and AP0.5 : 0.95 achieve 92.3% and 54.4%, respectively. The experimental results prove the effectiveness of the proposed method in detecting camouflage targets.
1 March 2025 in Journal of Electronic Imaging
We propose an algorithm for detecting inshore ship targets in synthetic aperture radar (SAR) images, named MFF-YOLO (You Only Look Once of multivariate feature fusion). On the basis of YOLOv5, the weakly supervised saliency feature module is constructed to enhance the feature texture under the supervision of weakly supervised labels, extract the multi-scale saliency target features, solve the problem that it is difficult to locate potential target regions in the SAR image with insufficient inshore target features, and improve the recall rate by 3.2%; the land–sea feature module is constructed to extract the land–sea distribution features of the image, suppress the land area features, solve the problem of high false alarm rate caused by land clutter in inshore scenes, and improve the precision rate by 3.2%; construct multivariate feature fusion module to fuse the target features, weakly supervised saliency features and land–sea distribution features in multiple scales; and use adaptive thresholding to suppress irrelevant noise to obtain target features enhanced by multivariate features fusion, which solves the problems of insufficient target available information and irrelevant noise interference in SAR images, improves AP0.5 by 3.3%, and improves F1 measure by 2%. This algorithm achieves a precision of 88.3% on the inshore portion of the high-resolution SAR image dataset, a recall of 77.5%, an AP0.5 of 81.6%, and an F1 of 0.825, demonstrating superior detection performance over other comparative algorithms, with good accuracy and robustness.
1 August 2023 in AIP Advances
An algorithm based on the spectral segment fusion combination and deep residual network is proposed to improve the recognition accuracy of the objects of interest in the WHU-Hi dataset, particularly for cruciferous plants. The accuracy of the objects of interest was effectively improved, as well as the recognition accuracy of other ground objects, and the time efficiency was improved as well. The optimal combination of spectral segments was determined, and spatial and spectral information was extracted from the deep residual network for ground object recognition research. Experimental results showed that the classification accuracy of the cruciferous plants of interest, namely, pak choi, Brassica chinensis, and small Brassica chinensis, increased from 81.36%, 84.2%, and 83.8% to 98.32%, 99.22%, and 98.35%, respectively. In addition, the accuracy of interested trees and grass also increased from 77.6% and 89.09% to 99.12% and 98.33%, respectively, and the overall accuracy, KAPPA, and average accuracy of the three datasets were all improved. The time efficiency was also improved by an order of magnitude.