Underwater captured images are usually degraded by low contrast, hazy, and blurry due to absorbing and scattering, which limits their analyses and applications. To address these problems, a red channel prior guided variational framework is proposed based on the complete underwater image formation model (UIFM). Unlike most of the existing methods that only consider the direct transmission and backscattering components, we additionally include forward scattering component into the UIFM. In the proposed variational framework, we successfully incorporate the normalized total variation item and sparse prior knowledge of blur kernel together. In addition, we perform the estimation of blur kernel by varying image resolution in a coarse-to-fine manner to avoid local minima. Moreover, for solving the generated non-smooth optimization problem, we employ the alternating direction method of multipliers (ADMM) to accelerate the whole progress. Experimental results demonstrate that the proposed method has a good performance on dehazing and deblurring. Extensive qualitative and quantitative comparisons further validate its superiority against the other state-of-the-art algorithms. The code is available online at: https://github.com/Hou-Guojia/UNTV

Achieving subjective and objective quality assessment of underwater images is of high significance in underwater visual perception and image/video processing. However, the development of underwater image quality assessment (UIQA) is limited for the lack of publicly available underwater image datasets with human subjective scores and reliable objective UIQA metrics. To address this issue, we establish a large-scale underwater image dataset, dubbed UID2021, for evaluating no-reference (NR) UIQA metrics. The constructed dataset contains 60 multiply degraded underwater images collected from various sources, covering six common underwater scenes (i.e., bluish scene, blue-green scene, greenish scene, hazy scene, low-light scene, and turbid scene), and their corresponding 900 quality improved versions are generated by employing 15 state-of-the-art underwater image enhancement and restoration algorithms. Mean opinion scores with 52 observers for each image of UID2021 are also obtained by using the pairwise comparison sorting method. Both in-air and underwater-specific NR IQA algorithms are tested on our constructed dataset to fairly compare their performance and analyze their strengths and weaknesses. Our proposed UID2021 dataset enables ones to evaluate NR UIQA algorithms comprehensively and paves the way for further research on UIQA. The dataset is available at https://github.com/Hou-Guojia/UID2021 .

The problem of routing security in vehicular adhoc networks (i.e., VANETs) has become a major concern for researchers. Compared with cryptography-based solutions, trust-based solutions are considered to be more acceptable as a promising approach, which mainly define two operations: trust computing and security application. We first study trust properties and construct a novel trust inference model, where two trust attributes named subjective trust and recommendation trust, are selected to quantify the trust level of a specific vehicle. The SCGM(1,1)-weighted Markov prediction algorithm based on fluctuation recognition is utilized to calculate the subjective trust accurately, meanwhile a new evaluation method of recommendation credibility based on the feedback mechanism is introduced for the calculation of recommendation trust. We subsequently exploit the advantages of mesh structure and design a light-weight trust-aware multicast routing protocol (i.e., LTMRP), which can establish secure and reliable communication paths by selecting trusted relay vehicles. To further improve the routing efficiency, two mechanisms including forwarding nodes reuse mechanism and trust-aware route handoff mechanism are proposed. Simulation verification and comparison of the relevant trust models and trust-based protocols are accomplished by three simulation platforms (i.e., Netlogo, SUMO and NS-2).The convincing results show that our trust model obtains strong resistibility to multiple malicious attacks. Moreover, examined in four routing metrics, the experimental results indicate that LTMRP performs better than the other relevant protocols.

The lightweight design of vehicle components is regarded as a complex optimization problem, which usually needs to achieve two or more optimization objectives. It can be firstly solved by a multi-objective optimization algorithm for generating Pareto solutions, before then seeking the optimal design. However, it is difficult to determine the optimal design for lack of engineering knowledge about ideal and nadir values. Therefore, this paper proposes a multi-objective optimization procedure combined with the NSGA-II algorithm with entropy weighted TOPSIS for the lightweight design of the dump truck carriage. The finite element model of the dump truck carriage was firstly developed for modal analysis under unconstrained free state and strength analysis under the full load and lifting conditions. On this basis, the multi-objective lightweight optimization of the dump truck carriage was carried out based on the Kriging surrogate model and the NSGA-II algorithm. Then, the entropy weight TOPSIS method was employed to select the optimal design of the dump truck from Pareto solutions. The results show that the optimized dump truck carriage achieves a remarkable mass reduction of 81 kg, as much as 3.7%, while its first-order natural frequency and strength performance are slightly improved compared with the original model. Accordingly, the proposed procedure provides an effective way for vehicle lightweight design.

This paper advocates a novel learning solution to the modeling of long-term spatial-temporal saliency consistency in order to boost the accuracy for video saliency detection. Conventional methods typically utilize the “slack” spatial-temporal model to locally ensure the smoothness of the computed video saliency, yet they could easily encounter the performance tradeoff dilemma (i.e., detection’ accuracy and integrity). In contrast, our novel approach proposes the bi-level learning strategy to globally exploit the saliency consistency while overcoming the above difficulty. Our method first starts with the contrast computation of low-level saliency clues in a frame-wise manner. Then, based on such obtained saliency clues, we devise a novel bilevel Markov Random Field (bMRF) solution to conduct semantic labelling, which can explicitly indicates both the salient salient foregrounds and non-salient nearby surroundings with high confidence while shrinking the low confidence remains. In such a way, the spatial-temporal consistency constraint is embedded intrinsically into the above explicit semantic labels, and we avoid the performance trade-off problem from occurring. Next, based on those semantic labels made by our bMRF method, we further propose to learn multiple non-linear feature transformations to enlarge the feature margin between the salient foregrounds and the non-salient nearby surroundings, whose key rationale is to resort to long-term common consistencies to enforce the spatial-temporal smoothness. Thus, we can utilize these learned non-linear feature transformations to simultaneously suppress those short-term false-alarms and correct those hollow effects. To validate our new approach, we conduct extensive experiments on 5 publicly available benchmarks, and make comprehensive, quantitative evaluations between our method and 17 state-ofthe- art techniques. All the results demonstrate our method’s advantages in terms of accuracy, reliability, robustness, and versatility.