Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy but not on the boundary quality. In this paper, we propose a predict-refine architecture, BASNet, and a new hybrid loss for Boundary-Aware Salient object detection. Specifically, the architecture is composed of a densely supervised Encoder-Decoder network and a residual refinement module, which are respectively in charge of saliency prediction and saliency map refinement. The hybrid loss guides the network to learn the transformation between the input image and the ground truth in a three-level hierarchy -- pixel-, patch- and map- level -- by fusing Binary Cross Entropy (BCE), Structural SIMilarity (SSIM) and Intersection-over-Union (IoU) losses. Equipped with the hybrid loss, the proposed predict-refine architecture is able to effectively segment the salient object regions and accurately predict the fine structures with clear boundaries. Experimental results on six public datasets show that our method outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures. Our method runs at over 25 fps on a single GPU. The code is available at: https://github.com/NathanUA/BASNet.
This paper presents a novel boundary based semiautomatic tool, ByLabel, for accurate image annotation. Given an image, ByLabel first detects its edge features and computes high quality boundary fragments. Current labeling tools require the human to accurately click on numerous boundary points. ByLabel simplifies this to just selecting among the boundary fragment proposals that ByLabel automatically generates. To evaluate the performance of By-Label, 10 volunteers, with no experiences of annotation, labeled both synthetic and real images. Compared to the commonly used tool LabelMe, ByLabel reduces image-clicks and time by 73% and 56% respectively, while improving the accuracy by 73% (from 1.1 pixel average boundary error to 0.3 pixel). The results show that our ByLabel outperforms the state-of-the-art annotation tool in terms of efficiency, accuracy and user experience. The tool is publicly available: http://webdocs.cs.ualberta.ca/~vis/ bylabel/.
This work proposes a model predictive control (MPC) approach for a switching linear system where the switching signal is prescribed with unknown future values. The switching signal is known only at its current value, satisfies a minimal dwell-time restriction of τ steps between successive switchings and is otherwise arbitrary. Under such a setting, the MPC optimization problem has to allow for all admissible switching sequences within a given horizon length. Such a formulation necessitates several other features: the use of a modified returnable set as the terminal constraint; the introduction of consistency constraints on the predicted controls; a min-max optimization criterion as the cost function; the splitting of the horizon into two portions for recursive feasibility consideration and exponential stability of the closed-loop system. The proposed approach is demonstrated by a numerical example.
This letter presents a novel approach for extracting accurate outlines of individual buildings from very high-resolution (0.1-0.4 m) optical images. Building outlines are defined as polygons here. Our approach operates on a set of straight line segments that are detected by a line detector. It groups a subset of detected line segments and connects them to form a closed polygon. Particularly, a new grouping cost is defined first. Second, a weighted undirected graph G(V,E) is constructed based on the endpoints of those extracted line segments. The building outline extraction is then formulated as a problem of searching for a graph cycle with the minimal grouping cost. To solve the graph cycle searching problem, the bidirectional shortest path method is utilized. Our method is validated on a newly created data set that contains 123 images of various building roofs with different shapes, sizes, and intensities. The experimental results with an average intersection-over-union of 90.56% and an average alignment error of 6.56 pixels demonstrate that our approach is robust to different shapes of building roofs and outperforms the state-of-the-art method.