LGA-YOLO for Vehicle Detection in Remote Sensing Images
Yin Zhang, Weiyang Wang, Mu Ye, Junhua Yan, Rong Yang
Abstract
In remote sensing images, vehicles often appear on a minuscule scale, lacking features and easily overwhelmed by intricate background information. This becomes even more challenging in low illumination or occluded environments, leading to missed detections and false alarms. A novel vehicle detection algorithm, known as local and global aware YOLO (LGA-YOLO), is introduced to tackle these issues. LGA-YOLO incorporates two innovative and plug-and-play modules: the multiscale large kernel local aware module (MLKM) and the directional global context aware module (DGAM). MLKM widens the receptive field and enhances local features, while DGAM gathers global context information, highlighting vehicle features against complex backgrounds. Based on these modules, a high-low feature fusion network is reconstructed, capturing multiscale object features and effectively leveraging shallow features. Our self-constructed dataset (USOD), VEDAI, and DOTA are employed to validate LGA-YOLO's efficacy. In USOD, the results demonstrate the remarkable performance of LGA-YOLO, with precision, recall, AP<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0.5</sub>, and AP<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0.5:0.95</sub> scores of 0.927, 0.889, 0.930, and 0.371, respectively. In VEDAI and DOTA, the mAP<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0.5</sub> of LGA-YOLO reaches 0.803 and 0.781, respectively. These metrics not only surpass baseline models but also leading-edge algorithms in the field.