SRN: Side-Output Residual Network for Object Reflection Symmetry Detection and Beyond

Image Enhancement Guided Object Detection in Visually Degraded Scenes

Object detection accuracy degrades seriously in visually degraded scenes. A natural solution is to first enhance the degraded image and then perform object detection. However, it is suboptimal and does not necessarily lead to the improvement of object detection due to the separation of the image enhancement and object detection tasks. To solve this problem, we propose an image enhancement guided object detection method, which refines the detection network with an additional enhancement branch in an end-to-end way. Specifically, the enhancement branch and detection branch are organized in a parallel way, and a feature guided module is designed to connect the two branches, which optimizes the shallow feature of the input image in the detection branch to be as consistent as possible with that of the enhanced image. As the enhancement branch is frozen during training, such a design plays a role in using the features of enhanced images to guide the learning of object detection branch, so as to make the learned detection branch being aware of both image quality and object detection. When testing, the enhancement branch and feature guided module are removed, and so no additional computation cost is introduced for detection. Extensive experimental results, on underwater, hazy, and low-light object detection datasets, demonstrate that the proposed method can improve the detection performance of popular detection networks (YOLO v3, Faster R-CNN, DetectoRS) significantly in visually degraded scenes.

A Method to Improve the Accuracy of Pavement Crack Identification by Combining a Semantic Segmentation and Edge Detection Model

In recent years, deep learning-based detection methods have been applied to pavement crack detection. In practical applications, surface cracks are divided into inner and edge regions for pavements with rough surfaces and complex environments. This creates difficulties in the image detection task. This paper is inspired by the U-Net semantic segmentation network and holistically nested edge detection network. A side-output part is added to the U-Net decoder that performs edge extraction and deep supervision. A network model combining two tasks that can output the semantic segmentation results of the crack image and the edge detection results of different scales is proposed. The model can be used for other tasks that need both semantic segmentation and edge detection. Finally, the segmentation and edge images are fused using different methods to improve the crack detection accuracy. The experimental results show that mean intersection over union reaches 69.32 on our dataset and 61.05 on another pavement dataset group that did not participate in training. Our model is better than other detection methods based on deep learning. The proposed method can increase the MIoU value by up to 5.55 and increase the MPA value by up to 10.41 when compared to previous semantic segmentation models.

Image Co-Skeletonization via Co-Segmentation

Recent advances in the joint processing of a set of images have shown its advantages over individual processing. Unlike the existing works geared towards co-segmentation or co-localization, in this article, we explore a new joint processing topic: image co-skeletonization, which is defined as joint skeleton extraction of the foreground objects in an image collection. It is well known that object skeletonization in a single natural image is challenging, because there is hardly any prior knowledge available about the object present in the image. Therefore, we resort to the idea of image co-skeletonization, hoping that the commonness prior that exists across the semantically similar images can be leveraged to have such knowledge, similar to other joint processing problems such as co-segmentation. Moreover, earlier research has found that augmenting a skeletonization process with the object's shape information is highly beneficial in capturing the image context. Having made these two observations, we propose a coupled framework for co-skeletonization and co-segmentation tasks to facilitate shape information discovery for our co-skeletonization process through the co-segmentation process. While image co-skeletonization is our primary goal, the co-segmentation process might also benefit, in turn, from exploiting skeleton outputs of the co-skeletonization process as central object seeds through such a coupled framework. As a result, both can benefit from each other synergistically. For evaluating image co-skeletonization results, we also construct a novel benchmark dataset by annotating nearly 1.8 K images and dividing them into 38 semantic categories. Although the proposed idea is essentially a weakly supervised method, it can also be employed in supervised and unsupervised scenarios. Extensive experiments demonstrate that the proposed method achieves promising results in all three scenarios.