The research community has increasing interest in autonomous driving research, despite the resource intensity of obtaining representative real world data. Existing selfdriving datasets are limited in the scale and variation of the environments they capture, even though generalization within and between operating regions is crucial to the overall viability of the technology. In an effort to help align the research community's contributions with real-world selfdriving problems, we introduce a new large scale, high quality, diverse dataset. Our new dataset consists of 1150 scenes that each span 20 seconds, consisting of well synchronized and calibrated high quality LiDAR and camera data captured across a range of urban and suburban geographies. It is 15x more diverse than the largest camera+LiDAR dataset available based on our proposed diversity metric. We exhaustively annotated this data with 2D (camera image) and 3D (LiDAR) bounding boxes, with consistent identifiers across frames. Finally, we provide strong baselines for 2D as well as 3D detection and tracking tasks. We further study the effects of dataset size and generalization across geographies on 3D detection methods. Find data, code and more up-todate information at http://www.waymo.com/open.
Image segmentation has been increasingly used to identify the particle size distribution of crushed ore; however, the adhesion of ore particles and dark areas in the images of blast heaps and conveyor belts usually results in lower segmentation accuracy. To overcome this issue, an image segmentation method UR based on deep learning U-Net and Res_Unet networks is proposed in this study. Gray-scale, median filter and adaptive histogram equalization techniques are used to preprocess the original ore images captured from an open pit mine to reduce noise and extract the target region. U-Net and Res_Unet are utilized to generate ore contour detection and optimization models, and the ore image segmentation result is illustrated by OpenCV. The efficiency and accuracy of the newly proposed UR method is demonstrated and validated by comparing with the existing image segmentation methods. Fig. 8 The segmentation results of the conveyor images are obtained by different methods. (a) Original image, (b) NUR method, (c) watershed algorithm based on morphological reconstruction, (d) UR method.This journal is
In this paper, we study regional discrimination in a peer-to-peer lending scenario and provide novel empirical evidence for theories of soft information collection and information cost.We find that the regional information matters for borrowers' funding probabilities and that discrimination is profit-oriented or taste-oriented depending on the specific region. Moreover, using borrowers' birthplace as an instrumental variable, we find no evidence of genuine discrimination based purely on region in the peer-to-peer lending market.
Although the previous studies investigating the relationship between credit ratings and spread or return in the financial market are normally restricted to noncausal measures, this paper uses structural equation modelling to test the possibility of causal links from ratings to spread and return in the context of structured finance products. Our analyses are split into 2 stages: First, we search for causality between ratings and spread at the issuance stage (primary market) based on a sample comprising all tranches of asset‐backed securities issued in the United States by American and foreign institutions from December 1999 to December 2015. Then, we consider all ABS rating changes from February 2001 to December 2015 to check whether the assumption of causal connection between ratings and return at the trading stage (secondary market) is reasonable. After testing all pertinent combinations among the variables in our database, we find evidence of causality at the issuance stage but very little support to causality at the trading stage. This study contributes to the debate on the regulation of credit rating agencies as our findings suggest that ratings may have an effective influence on decisions made by investors at the time structure finance products are issued. As this effect is very weak when those assets are traded in the secondary market, in principle, regulators should focus their attention on the credit rating agencies' activities regarding the issuance of new structured products.
In recent years there has been a growing interest in the study of sparse representation of signals. The redundancy of over-complete dictionary can make it effectively capture the characteristics of the signals. Using an over-complete dictionary that contains prototype signal-atoms, signals are described as linear combinations of a few of these atoms. Applications that use sparse representation are many and include compression, regularization in inverse problems, Compressed Sensing (CS), and more. Recent activities in this field concentrate mainly on the study of sparse decomposition algorithm and dictionary design algorithm. In this paper, we discuss the advantages of sparse dictionaries, and present the implicit dictionaries for signal sparse presents. The overcomplete dictionaries which combined the different orthonormal transform bases can be used for the compressed sensing. Experimental results demonstrate the effectivity for sparse presents of signals.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.