Road Object Detection Using a Disparity-Based Fusion Model

Detection methods based on 2-D images tend to extract the color, texture, shape, and other appearance features of objects. However, in complex scenes, the detection results using these methods are often influenced by shadows, occlusion, and resolution. In this paper, a disparity-proposal-based detection method that rapidly extracts candidate frames of the detection objects on the basis of stereo disparity and ensures the robustness of the candidate frames under different perturbations is proposed. Furthermore, depth information is used to construct multi-scale pooling layers, allowing objects of different sizes to activate different layers at different levels. The detection model incorporates 2-D image features and 3-D geometric features and overcomes the limitations of the 2-D detection methods (absence of depth information) by using disparity features. Based on the experimental results, this method effectively achieves on-road object detection in complex scenes.