Object Detection Based on Faster R-CNN Algorithm with Skip Pooling and Fusion of Contextual Information

Abstract

Deep learning is currently the mainstream method of object detection. Faster region-based convolutional neural network (Faster R-CNN) has a pivotal position in deep learning. It has impressive detection effects in ordinary scenes. However, under special conditions, there can still be unsatisfactory detection performance, such as the object having problems like occlusion, deformation, or small size. This paper proposes a novel and improved algorithm based on the Faster R-CNN framework combined with the Faster R-CNN algorithm with skip pooling and fusion of contextual information. This algorithm can improve the detection performance under special conditions on the basis of Faster R-CNN. The improvement mainly has three parts: The first part adds a context information feature extraction model after the conv5_3 of the convolutional layer; the second part adds skip pooling so that the former can fully obtain the contextual information of the object, especially for situations where the object is occluded and deformed; and the third part replaces the region proposal network (RPN) with a more efficient guided anchor RPN (GA-RPN), which can maintain the recall rate while improving the detection performance. The latter can obtain more detailed information from different feature layers of the deep neural network algorithm, and is especially aimed at scenes with small objects. Compared with Faster R-CNN, you only look once series (such as: YOLOv3), single shot detector (such as: SSD512), and other object detection algorithms, the algorithm proposed in this paper has an average improvement of 6.857% on the mean average precision (mAP) evaluation index while maintaining a certain recall rate. This strongly proves that the proposed method has higher detection rate and detection efficiency in this case.

A Region-Based Efficient Network for Accurate Object Detection

“…The slow detection speed remains a big challenge for this model. Xiao et al [50] introduced an efficient detection model that retains the legacy of regionbased CNNs. The model integrates skip pooling with contextual information instead of RPN, thereby realizing improved performance.…”

Improved SSD-assisted algorithm for surface defect detection of electromagnetic luminescence

“…The proposed method is evaluated by comparing it with traditional machine vision algorithms, such as SIFT, 26 Fast R-CNN, 27 and YOLOv3, 28 by using the same image dataset. SIFT algorithm can also extract feature points, but robustness and accuracy are lower than those of our algorithm.…”

Comparative Study of Vehicle Detection using SSD and Faster RCNN

“…The ROIwill reduce the various sizes of feature maps into same size feature maps by using the Max-Pooling Method. This network was an improved algorithm based on ResNet-50 [1] network, and its detection accuracy was higher in range because it detects small objects.…”