No abstract

No abstract

Existing state-of-the-art minimal path techniques work well to extract simple open curves in images when both endpoints of the curve are given as user input or when one input is given and the total length of the curve is known in advance. Curves which branch require even further prior input from the user, namely, each branch endpoint. In this work, we present a novel minimal path-based algorithm which works on much more general curve topologies with far fewer demands on the user for initial input compared to prior minimal path-based algorithms. The two key novelties and benefits of this new approach are that 1) it may be used to detect both open and closed curves, including more complex topologies containing both multiple branch points and multiple closed cycles without requiring a priori knowledge about which of these types is to be extracted, and 2) it requires only a single input point which, in contrast to existing methods, is no longer constrained to be an endpoint of the desired curve but may in fact be ANY point along the desired curve (even an internal point). We perform quantitative evaluation of the algorithm on 48 images (44 pavement crack images, 1 catheter tube image, and 3 retinal images) against human supplied ground truth. The results demonstrate that the algorithm is indeed able to extract curve-like objects accurately from images with far less prior knowledge and less user interaction compared to existing state-of-the-art minimal path-based image processing algorithms. In the future, the algorithm can be applied to other 2D curve-like objects and it can be extended to detect 3D curves.

No abstract

Single image dehazing is the ill-posed two-dimensional signal reconstruction problem. Recently, deep convolutional neural networks (CNN) have been successfully used in many computer vision problems. In this paper, we propose a Y-net that is named for its structure. This network reconstructs clear images by aggregating multi-scale features maps. Additionally, we propose a Wavelet Structure SIMilarity (W-SSIM) loss function in the training step. In the proposed loss function, discrete wavelet transforms are applied repeatedly to divide the image into differently sized patches with different frequencies and scales. The proposed loss function is the accumulation of SSIM loss of various patches with respective ratios. Extensive experimental results demonstrate that the proposed Y-net with the W-SSIM loss function restores high-quality clear images and outperforms stateof-the-art algorithms. Code and models are available at https://github.com/dectrfov/Y-net Index Terms-Single image dehazing, Y-net, discrete wavelet transform, structure similarity, multi-scale feature aggregation

No abstract

No abstract

Traffic signs are transportation assets important for roadway safety. Traffic sign attributes are typically collected manually in the field, which is timeconsuming, costly, and dangerous. This article proposes an algorithm to extract traffic sign attributes, including height, tilted angle, location, and sign-to-camera distance, from video log images. The article makes two contributions. First, the article develops an algorithm that computes traffic sign attributes by applying a homographybased computation model. The algorithm has four main steps: homography computation, camera calibration, sign pose calculation, and computation of traffic sign attributes. Second, the article uses three-coordinate systems to solve out-of-view and occlusion problems; sign attributes can be computed when the bottom of a sign is occluded by objects like grass or is not available in the image due to the camera's angle of view. Simulation data was first used to test the algorithm performance with different noise levels, sign-to-camera distances, and calibration errors, which are difficult to obtain from real data. A typical 60 cm × 75 cm rectangular speed limit sign, 3 m high and with a 6 • tilted angle, was created for the simulation. Under a typical 8 m measurement distance and 0.5 pixel noise level, the computed sign angle has an error of 0.4 • with a standard deviation of 4.0 • . The means and standard deviations for the errors of the height and sign-to-camera distance are 10 cm, 18 cm, and 1 cm,