Crack is one of the most common road distresses which may pose road safety hazards. Generally, crack detection is performed by either certified inspectors or structural engineers. This task is, however, time-consuming, subjective and labor-intensive. In this paper, we propose a novel road crack detection algorithm based on deep learning and adaptive image segmentation. Firstly, a deep convolutional neural network is trained to determine whether an image contains cracks or not. The images containing cracks are then smoothed using bilateral filtering, which greatly minimizes the number of noisy pixels. Finally, we utilize an adaptive thresholding method to extract the cracks from road surface. The experimental results illustrate that our network can classify images with an accuracy of 99.92%, and the cracks can be successfully extracted from the images using our proposed thresholding algorithm. 1 R. Fan, J. Jiao and M. Liu are with the Robotics and Multi-Perception Laboratory in Robotics Institute at

Combining multiple LiDARs enables a robot to maximize its perceptual awareness of environments and obtain sufficient measurements, which is promising for simultaneous localization and mapping (SLAM). This paper proposes a system to achieve robust and simultaneous extrinsic calibration, odometry, and mapping for a multiple LiDARs. Our approach starts with measurement preprocessing to extract edge and planar features from raw measurements. After a motion and extrinsic initialization procedure, a sliding window-based multi-LiDAR odometry runs onboard to estimate poses with online calibration refinement and convergence identification. We further develop a mapping algorithm to construct a global map and optimize poses with sufficient features together with a method to model and reduce data uncertainty. We validate our approach's performance with extensive experiments on ten sequences (4.60km total length) for the calibration and SLAM and compare them against the state-of-the-art. We demonstrate that the proposed work is a complete, robust, and extensible system for various multi-LiDAR setups. The source code, datasets, and demonstrations are available at: https://ram-lab.com/file/site/m-loam.

The objective of this study was to track the dynamic variations in fecal bacterial composition and fermentation profile of finishing steers in response to three stepwise diets varied in energy and protein density. A total of 18 Holstein steers were divided into three groups in such a way that each group contained six animals and received one of three stepwise dietary treatments. Dietary treatments were C = standard energy and protein diet, H = high energy and protein diet, and L = low energy and protein diet. Animals were fattened for 11 months with a three-phase fattening strategy. Fecal samples were collected to evaluate the dynamics of fecal fermentation and bacterial composition in response to dietary treatments and fattening phases using 16S rRNA gene sequencing. Fecal acetate, propionate, and butyrate increased with increasing density of diet and as the fattening phase continued. The relative abundances of Firmicutes and Bacteroidetes dominated and showed 56.19% and 33.58%, respectively. Higher dietary density decreased the fecal bacterial diversity, Firmicutes to Bacteroidetes ratio, and the relative abundances of Ruminococcaceae_UCG-005, Rikenellaceae_RC9_gut_group, and Bacteroides, whereas higher dietary density increased the abundance of Prevotella_9. Our results indicated that both fecal fermentation profile and bacterial composition share a time-dependent variation in response to different dietary densities. This knowledge highlights that both diet and fattening phase impact fecal fermentation profile and bacterial composition, and may provide insight into strategies to reduce fecal contamination from the origin by optimizing diet and fattening time.

No abstract