Search

Recently, deep learning has made impressive achievements in low-light image enhancement. Most existing deep learning-based methods use convolutional neural networks (CNN) by stacking network depth and modifying network architecture to improve feature extraction capabilities and restore degraded images. However, these methods have obvious defects. Although CNN excels at extracting local features, its small receptive field is unable to capture the global brightness, leading to overexposure. The Transformer model from natural language processing has recently produced positive outcomes in a variety of computer vision issues thanks to its excellent global modeling capabilities. However, its complex modeling method makes it difficult to capture local details and takes up many computing resources, making it challenging to apply to the enhancement of low-light images, especially high-resolution images. Based on deep convolution and Transformer characteristics, this paper proposes a Transformer-CNN Parallel Cooperative Network (TCPCNet), which supplements image details and local brightness while ensuring global brightness control. We also changed the calculation method of the traditional Transformer to be applied to enhance high-resolution low-light images without affecting performance. Extensive experiments on public datasets show that the proposed TCPCNet achieves comparable performance against the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Urban green space equity relates to the efficient allocation of natural resources and the equalization of public service facilities. Street (road) greenery provides substantial ecological, social and cultural benefits. Thus, in this study, a subdistrict-level evaluation framework for the fairness of the spatial distribution of street greenery was proposed, taking a case study within the Third Ring Road of Fuzhou City in Fujian, China. Street view images may capture the green information in a vertical dimension for the indirect representation of people's perspective on the ground. The green view index, which was estimated based on Baidu Street View images, was employed to represent the urban street greenery, and the results were combined using deep learning technology. The Gini coefficient, share index and location entropy were used as evaluation indicators for the fairness of the spatial distribution of the street green view index. Furthermore, this framework combined socioeconomic data and population census data to explore the correlation among socioeconomic status, age, and evaluation index at the subdistrict level. In addition, we analyzed street greenery distribution inequalities from the perspective of socioecological justice. The results showed that in Fuzhou, there is a significant correlation among the Gini coefficient, green view index and socioeconomic status. In addition, subdistricts with a lower green view index have a less equitable street greenery distribution, people with low socioeconomic status may suffer from green injustice, and seniors have a lower accessibility to street green space than people with the average social status. Our analytical approach is applicable for other cities, and the findings are useful for greenery spatial planning processes and evaluating construction effects. • Visible street greenery was evaluated using the green view index. • A framework for assessing the fairness of street greenery distribution was proposed. • Subdistricts in Fuzhou with a lower GVI value have more inequitable street greenery distributions. • Equitable access to green space is related to socioeconomic status and age. [ABSTRACT FROM AUTHOR]

Connected and Automated Vehicle (CAV) is a transformative technology that has great potential to improve urban traffic and driving safety. Electric Vehicle (EV) is becoming the key subject of next-generation CAVs by virtue of its advantages in energy saving. Due to the limited endurance and computing capacity of EVs, it is challenging to meet the surging demand for computing-intensive and delay-sensitive in-vehicle intelligent applications. Therefore, computation offloading has been employed to extend a single vehicle's computing capacity. Although various offloading strategies have been proposed to achieve good computing performace in the Vehicular Edge Computing (VEC) environment, it remains challenging to jointly optimize the offloading failure rate and the total energy consumption of the offloading process. To address this challenge, in this paper, we establish a computation offloading model based on Markov Decision Process (MDP), taking into consideration task dependencies, vehicle mobility, and different computing resources for task offloading. We then design a computation offloading strategy based on deep reinforcement learning, and leverage the Deep Q-Network based on Simulated Annealing (SA-DQN) algorithm to optimize the joint objectives. Experimental results show that the proposed strategy effectively reduces the offloading failure rate and the total energy consumption for application offloading. [ABSTRACT FROM AUTHOR]

Recently, blind image quality assessment (BIQA) has been intensively studied with deep learning. However, the limited quality-annotated datasets restrict its further development. Although patch-based methods have been leveraged to generate more training data, they usually assign the image quality score to all patches in an image. Consequently, much noise would be introduced. To avoid this, we propose a method learning distance distribution from quality levels to expand the training data, which is pseudo Siamese network-based no-reference image quality assessment (NR-IQA). Specifically, we firstly use the K-means clustering algorithm to classify the quality scores of distorted images into five levels. Subsequently, the pseudo Siamese network is adopted to learn the distance distribution from these quality levels. We mainly decrease distances between the quality scores of images from the same quality level and increase distances between the quality scores of images from different quality levels, in which the distorted images can be compared across different distortion types. Finally, we introduce a fusion layer to average the quality scores learnt by the two branches of the trained pseudo Siamese network, and take fine-tuning on this basis to learn image quality score from one image. To demonstrate the effectiveness of the proposed approach, we evaluate it on benchmark databases (LIVE, TID2013 and LIVE MD). The result shows superior performance to some widely used NR-IQA methods and full-reference IQA (FR-IQA) methods. Cross-database evaluation verifies high generalization ability and high effectiveness of our model. • We propose NR-IQA by learning distance distribution from quality levels. • The pseudo Siamese network is employed to learn the distance distribution. • A fusion layer is proposed to average the quality scores learnt by the Siamese network. • Cross-database evaluation verifies high generalization ability and effectiveness of our model. [ABSTRACT FROM AUTHOR]