UAV Image Small Object Detection Based on Composite Backbone Network

Abstract

Small objects in traffic scenes are difficult to detect. To improve the accuracy of small object detection using images taken by unmanned aerial vehicles (UAV), this study proposes a feature-enhancement detection algorithm based on a single shot multibox detector (SSD), named composite backbone single shot multibox detector (CBSSD), which uses a composite connection backbone to enhance feature representation. First, to enhance the detection effect of small objects, the lead backbone network, VGG16, is kept constant, and ResNet50 is added as an assistant backbone network, and the residual structure in ResNet50 is used to obtain lower feature information. The obtained lower feature information is then fused to the lead network through feature fusion, allowing the lead network to retain rich lower feature information. Finally, the lower feature information in the prediction layer increases. The experimental results show that CBSSD has a significantly higher recognition rate and a lower false detection rate than conventional algorithms, and it still maintains a good detection effect under low illumination. This is of great significance to small object detection using images taken by UAVs in traffic scenes. Furthermore, a method to improve the SSD algorithm is proposed.

MSSF-DCNet: multi-scale selective fusion with dense connectivity network for sonar image object detection

“…Within the realm of identifying objects, the neck network (Neck) plays a crucial role. The neck network is an intermediate component that bridges the backbone [13,14,15,16,17] network (Backbone) and the head network (Head) [18]. The backbone network extracts features from the input image, while the head network utilizes these features for object detection purposes.…”

YOLO Network-based URL Detection in Varied Conditions with Small-Sample Insights

“…These models have significantly propelled object detection technology, finding applications ranging from facial recognition to autonomous vehicles [6]. Moreover, advanced techniques have been proposed, such as an enhanced YOLOv3 method for small object detection, incorporating modules like DCM, CBAM, and multi-level fusion to enhance feature expression and accuracy [7].…”

YOLO-UAV: Object Detection Method of Unmanned Aerial Vehicle Imagery Based on Efficient Multi-Scale Feature Fusion

“…Liu et al [14] introduced the CBSSD method. Building on the foundation of VGG-16, CBSSD incorporated the ResNet-50 network as an auxiliary backbone, which enhanced feature extraction capabilities and facilitated the retention of richer semantic information.…”

“…mAP (Mean Average Precision) denotes the mean value of average precision across all individual categories. The mAP formula is shown in Equation (14).…”