PanoDetNet: Multi-Resolution Panoramic Object Detection With Adaptive Feature Attention

Panoramic image object detection has significant applications in autonomous driving, robotic navigation, and security monitoring. However, most current object detection algorithms are trained on pinhole images and cannot be directly applied to panoramic images, which have a large field-of-view (FOV) and distortion. Additionally, research on panoramic image object detection lacks dedicated dataset support, and these images face challenges such as target distortion, occlusion, and multi-scale variations. Existing methods for panoramic image object detection have not yielded satisfactory performance. To address these issues, we propose PanoDetNet, an object detection model based on YOLOv7. We introduce two new modules: the Multi-Scale Feature Fusion (MSFF) module and the Adaptive Panoramic Feature Attention (APFA) module. The MSFF module enhances detection precision for targets of different scales by fusing feature maps of various sizes, while also reducing the number of parameters and simplifying the model structure. The APFA module adaptively addresses the distortion in panoramic images, improving the model’s ability to locate and recognize objects in complex backgrounds and under occlusion. We trained PanoDetNet on our self-built panoramic image object detection dataset, PanoDet. This dataset was collected using a self-developed panoramic camera and manually annotated with the Labelme tool. Experimental results show that PanoDetNet achieves mAP@.5, mAP@.5:.95, and accuracy scores of 95.3%, 75.2%, and 94.1%, respectively. These results represent improvements of 1.6%, 2.5%, and 3.3% over YOLOv7. Our code is available at https://github.com/github98317/PanoDetNet.