Improving 2D object detection with binocular images for outdoor surveillance

Detecting objects and providing their 2D information (e.g., size and center) are crucial for outdoor visual surveillance. Because the cameras are static and their distances to background are fixed in the scenario of surveillance, we argue that, compared to 3D object detection, 2D object detection is usually enough in visual surveillance. To a great extent, determining the existence of objects is more important than determining their precise 3D shapes and locations. In the field of visual surveillance, almost all methods employ a single camera (or independently employing several cameras) to determine the existence and 2D information of objects. In this paper, we propose to improve the performance of the 2D object detection by binocular cameras (images) for the scenario of outdoor surveillance where RGB-D and depth cameras are not applicable due to their low resolutions and high expense. In the proposed binocular-image based 2D object detection framework, most of existing monocular-image based 2D object detection modules can be integrated in. Once integrated in the proposed framework, the object detection accuracy can significantly and consistently be improved. Experimental results on the challenging datasets of Cityscapes and KITTI demonstrate the superiority of the proposed method.