Computer‐vision and deep‐learning techniques are being increasingly applied to inspect, monitor, and assess infrastructure conditions including detection of cracks. Traditional vision‐based methods to detect cracks lack accuracy and generalization to work on complicated infrastructural conditions. This paper presents a novel context‐aware deep convolutional semantic segmentation network to effectively detect cracks in structural infrastructure under various conditions. The proposed method applies a pixel‐wise deep semantic segmentation network to segment the cracks on images with arbitrary sizes without retraining the prediction network. Meanwhile, a context‐aware fusion algorithm that leverages local cross‐state and cross‐space constraints is proposed to fuse the predictions of image patches. This method is evaluated on three datasets: CrackForest Dataset (CFD) and Tomorrows Road Infrastructure Monitoring, Management Dataset (TRIMMD) and a Customized Field Test Dataset (CFTD) and achieves Boundary F1 (BF) score of 0.8234, 0.8252, and 0.7937 under 2‐pixel error tolerance margin in CFD, TRIMMD, and CFTD, respectively. The proposed method advances the state‐of‐the‐art performance of BF score by approximately 2.71% in CFD, 1.47% in TRIMMD, and 4.14% in CFTD. Moreover, the averaged processing time of the proposed system is 0.7 s on a typical desktop with Intel® Quad‐Core™ i7‐7700 CPU@3.6 GHz Processor, 16GB RAM and NVIDIA GeForce GTX 1060 6GB GPU for an image of size 256 × 256 pixels.

No abstract

In rural China, successful and sustainable business model design has been viewed as an important strategy to achieve a win–win scenario in which rural poverty can be alleviated and enterprise profit can be improved. Although business model related literature is strong, it lacks a comprehensive framework for appraising business models in rural markets. As a result, entrepreneurs are facing significant challenges in implementing their market development centered business models or resource development centered business models. This study draws on case analysis to present two frameworks for evaluating the two types of business models, respectively. Through open coding and axial coding on eight Chinese cases, we identify the main components for the evaluation frameworks and critical factors within each component. Using the coding results as a lens, we apply a cross-case comparative data analysis to establish the multi-level evaluation systems. Finally, we provide suggestions for entrepreneurs and other stakeholders to better their business model design in China’s rural markets.

Continuous use is critical for the survival and success of any tourism online-to-offline (O2O) platforms. Much prior research has focused on initial trust on initial adoption of e-commerce websites but pays less attention to the effect of ongoing trust on continuous use. This study presents an integrated model, including two categories of ongoing trust to test their contributions on tourism O2O platform continuance. It also examines their different antecedents, impacts, and the interactions between them. Drawn from a web-based survey with 418 responses, empirical results show that ongoing trust in O2O platforms positively influence platform continuance, whereas ongoing trust in offline destinations positively influence ongoing trust in platforms. Confirmations of expected product and service quality are significant to ongoing trust in destinations, but confirmation of expected convenience is not. Confirmations of expected platform quality, specific guarantees, and loyalty program benefits are significant to ongoing trust in platforms. In addition, the antecedents and effects of ongoing trust in platforms are different between experienced and less-experienced customers. These findings have useful implications on how academics and practitioners work together to ensure the sustainable development of their tourism O2O businesses.

Computer-vision methods have recently been extensively used in intelligent transportation systems for vehicle detection. However, the detection of severely occluded or partially observed vehicles due to the limited camera fields of view remains a significant challenge. This paper presents a multi-camera vehicle detection system that significantly improves the detection performance under occlusion conditions. The key elements of the proposed method include a novel multi-view region proposal network that localizes the candidate vehicles on the ground plane. We also infer the vehicle occupancies by leveraging multi-view cross-camera context. Experiments are conducted on a dataset captured from a roadway in Richardson, TX, USA, and the proposed system attains 0.7849 Average Precision (AP) and 0.7089 Multi Object Detection Precision (MODP). The proposed system advances the single-view region proposal approaches by approximately 31.2% for AP and 8.6% for MODP. vi TABLE OF CONTENTS LIST OF FIGURES .