In this paper, we present a systematic review and evaluation of existing single-image low-light enhancement algorithms. Besides the commonly used low-level vision oriented evaluations, we additionally consider measuring machine vision performance in the low-light condition via face detection task to explore the potential of joint optimization of high-level and low-level vision enhancement. To this end, we first propose a large-scale low-light image dataset serving both low/high-level vision with diversified scenes and contents as well as complex degradation in real scenarios, called Vision Enhancement in the LOw-Light condition (VE-LOL). Beyond paired low/normal-light images without annotations, we additionally include the analysis resource related to human, i.e. face images in the low-light condition with annotated face bounding boxes. Then, efforts are made on benchmarking from the perspective of both human and machine visions. A rich variety of criteria is used for the low-level vision evaluation, including full-reference, no-reference, and semantic similarity metrics. We also measure the effects of the low-light enhancement on face detection in the low-light condition. State-of-the-art face detection methods are used in the evaluation. Furthermore, with the rich material of VE-LOL, we explore the novel problem of joint low-light enhancement and face detection. We develop an enhanced face detector to apply low-light enhancement and face detection jointly. The features extracted by the enhancement module are fed to the successive layer with the same resolution of the detection module. Thus, these features are intertwined together to unitedly learn useful information across two phases, i.e. enhancement and detection. Experiments on VE-LOL provide a comparison of state-of-the-art low-light enhancement algorithms, point out their limitations, and suggest promising future directions. Our dataset has supported the Track "Face Detection in Low Light Conditions" of CVPR UG2+ Challenge (2019-2020) (http://cvpr2020.ug2challenge.org/).

Retinex model is widely adopted in various low-light image enhancement tasks. The basic idea of the Retinex theory is to decompose images into reflectance and illumination. The ill-posed decomposition is usually handled by hand-crafted constraints and priors. With the recently emerging deep-learning based approaches as tools, in this paper, we integrate the idea of Retinex decomposition and semantic information awareness. Based on the observation that various objects and backgrounds have different material, reflection and perspective attributes, regions of a single low-light image may require different adjustment and enhancement regarding contrast, illumination and noise. We propose an enhancement pipeline with three parts that effectively utilize the semantic layer information. Specifically, we extract the segmentation, reflectance as well as illumination layers, and concurrently enhance every separate region,. . sky, ground and objects for outdoor scenes. Extensive experiments on both synthetic data and real world images demonstrate the superiority of our method over current state-ofthe-art low-light enhancement algorithms. Our code will be public available at: https://mm20-semanticreti.github.io/. CCS CONCEPTS • Computing methodologies → Image manipulation.

River ice monitoring is of great significance for river management, ship navigation and ice hazard forecasting in cold-regions. Accurate ice segmentation is one most important pieces of technology in ice monitoring research. It can provide the prerequisite information for the calculation of ice cover density, drift ice speed, ice cover distribution, change detection and so on. Unmanned aerial vehicle (UAV) aerial photography has the advantages of higher spatial and temporal resolution. As UAV technology has become more popular and cheaper, it has been widely used in ice monitoring. So, we focused on river ice segmentation based on UAV remote sensing images. In this study, the NWPU_YRCC dataset was built for river ice segmentation, in which all images were captured by different UAVs in the region of the Yellow River, the most difficult river to manage in the world. To the best of our knowledge, this is the first public UAV image dataset for river ice segmentation. Meanwhile, a semantic segmentation deep convolution neural network by fusing positional and channel-wise attentive features is proposed for river ice semantic segmentation, named ICENET. Experiments demonstrated that the proposed ICENET outperforms the state-of-the-art methods, achieving a superior result on the NWPU_YRCC dataset.

No abstract

Accurate ice segmentation is one of the most crucial techniques for intelligent ice monitoring. Compared with ice segmentation, it can provide more information for ice situation analysis, change trend prediction, and so on. Therefore, the study of ice segmentation has important practical significance. In this study, we focused on fine-grained river ice segmentation using unmanned aerial vehicle (UAV) images. This has the following difficulties: (1) The scale of river ice varies greatly in different images and even in the same image; (2) the same kind of river ice differs greatly in color, shape, texture, size, and so on; and (3) the appearances of different kinds of river ice sometimes appear similar due to the complex formation and change procedure. Therefore, to perform this study, the NWPU_YRCC2 dataset was built, in which all UAV images were collected in the Ningxia–Inner Mongolia reach of the Yellow River. Then, a novel semantic segmentation method based on deep convolution neural network, named ICENETv2, is proposed. To achieve multiscale accurate prediction, we design a multilevel features fusion framework, in which multi-scale high-level semantic features and lower-level finer features are effectively fused. Additionally, a dual attention module is adopted to highlight distinguishable characteristics, and a learnable up-sampling strategy is further used to improve the segmentation accuracy of the details. Experiments show that ICENETv2 achieves the state-of-the-art on the NWPU_YRCC2 dataset. Finally, our ICENETv2 is also applied to solve a realistic problem, calculating drift ice cover density, which is one of the most important factors to predict the freeze-up data of the river. The results demonstrate that the performance of ICENETv2 meets the actual application demand.

No abstract