Glass bottles must be thoroughly inspected before they are used for packaging. However, the vision inspection of bottle bottoms for defects remains a challenging task in quality control due to inaccurate localization, the difficulty in detecting defects in the texture region, and the intrinsically nonuniform brightness across the central panel. To overcome these problems, we propose a surface defect detection framework, which is composed of three main parts. First, a new localization method named entropy rate superpixel circle detection (ERSCD), which combines least-squares circle detection and entropy rate superpixel (ERS) with an improved randomized circle detection, is proposed to accurately obtain the region of interest (ROI) of the bottle bottom. Then, according to the structure-property, the ROI is divided into two measurement regions: central panel region and annular texture region. For the former, a defect detection method named frequency-tuned anisotropic diffusion super-pixel segmentation (FTADSP) that integrates frequency-tuned salient region detection (FT), anisotropic diffusion, and an improved superpixel segmentation is proposed to precisely detect the regions and boundaries of defects. For the latter, a defect detection strategy called wavelet transform multiscale filtering (WTMF) based on a wavelet transform and a multiscale filtering algorithm is proposed to reduce the influence of texture and to improve the robustness to localization error. The proposed framework is tested on four data sets obtained by our designed vision system. The experimental results demonstrate that our framework achieves the best performance compared with many traditional methods.

Learning a robust object detector in adverse weather with real-time efficiency is of great importance for the visual perception task for autonomous driving systems. In this paper, we propose a framework to improve the YOLO to a robust detector, denoted as R(obust)-YOLO, without the need for annotations in adverse weather. Considering the distribution gap between the normal weather images and the adverse weather images, our framework consists of an image quasi-translation network (QTNet) and a feature calibration network (FCNet) for adapting the normal weather domain to the adverse weather domain gradually. Specifically, we use the simple yet effective QTNet for generating images that inherit the annotations in the normal weather domain and interpolate the gap between the two domains. Then, in FCNet, we propose two kinds of adversarial learning-based feature calibration modules to effectively align the feature representations in two domains in a local-to-global manner. With such a learning framework, our R-YOLO does not change the original YOLO structure, and thus it is applicable to all YOLO-series detectors. Extensive experimental results of our R-YOLOv3, R-YOLOv5, and R-YOLOX on both hazy and rainy datasets show that our method outperforms other detectors with dehaze/derain as the pre-processing step and other unsupervised domain adaptation-based detectors, which confirms the effectiveness of our method on improving the robustness by only leveraging the unlabeled adverse weather images. Our code and pre-trained models are available at: https://github.com/qinhongda8/R-YOLO.

Single image defogging algorithms based on prior assumptions or constraints have captured much attention because of their simplicity and practicality. However, they still have some challenges to deal with foggy images captured under weather conditions where these assumptions or constraints may not be effective or efficient enough. In this paper, we aim to develop a novel image defogging algorithm by directly predicting the fog density of recovered images rather than adopting prior assumptions or constraints. In order to achieve this goal, two specific steps are introduced. First, we adopt three fog-relevant statistical features derived from foggy images, and further develop a simple fog density evaluator (SFDE) by creating a linear combination of these fog-relevant features. This proposed evaluator can efficiently perceive the fog density of a single image without reference to a corresponding fog-free image and has a low computational load compared with an existing method. Second, a physics-based mathematical relationship between the transmission and the fog density score of the recovered image is developed via SFDE, thus image defogging can be posed as a minimization problem on the fog density score of the recovered image. As a result, two optimal transmission models, called an Optimal Transmission model via SFDE (OTSFDE) and a Simpler Optimal Transmission models via SFDE (SOTSFDE), are present to determine the key transmission map for efficient fog removal. Compared to OTSFDE, SOTSFDE has low computational complexity with slight performance degradation. Experimental results demonstrate that the proposed algorithms can effectively remove fog and are not confined by any assumptions or constraints, both quantitatively and qualitatively, compared with some existing algorithms.

Previous methods in salient object detection (SOD) mainly focused on favorable illumination circumstances while neglecting the performance in low-light condition, which significantly impedes the development of related down-stream tasks. In this work, considering that it is impractical to annotate the large-scale labels for this task, we present a framework (HDNet) to detect the salient objects in low-light images with the synthetic images. Our HDNet consists of a foreground highlight sub-network (HNet) and an appearance-aware detection sub-network (DNet), both of which can be learned jointly in an end-to-end manner. Specifically, to highlight the foreground objects, we design the HNet to estimate the parameters to adjust the dynamic range for each pixel adaptively, which can be trained via the weak supervision signals of the salient object labels. In addition, we design a simple detection network (DNet) with a contextual feature fusion module and a multi-scale feature refine module for detailed feature fusion and refinement. Furthermore, we contribute the first annotated dataset for salient object detection in low-light images (SOD-LL), including 6,000 labeled synthetic images (SOD-LLS) and 2,000 labeled real images (SOD-LLR). Experimental results on SOD-LL and other low-light videos in the wild demonstrate the effectiveness and generalization ability of our method. Our dataset and code are available at https://github.com/Ylinyuan/HDNet.

Traffic sign recognition is a rather challenging task for intelligent transportation systems since signs in different subsets, e.g., speed limit signs, prohibition signs, and mandatory signs, are very different from each other in color or shape, whereas they share some similarities to the ones in the same subset. Therefore, it is important to integrate different modalities of visual features, such as color and shape, and select discriminative features for better sign description; in addition, it benefits to explore the correlations between the classes of traffic signs to learn the classifiers jointly to improve the generalization performance. In this paper, we propose Multi- Modal tree-structure embedded Multi-Task Learning called M ² - tMTL to select discriminative visual features both between and within modalities, as well as the correlated features shared by similar classification tasks. Our method simultaneously introduces two structured sparsity-induced norms into a least squares regression. One of the norms can be used not only to select modality of features but also to conduct within-modality feature selection. Moreover, the hierarchical correlations among the classification tasks are well represented by a tree structure, and therefore, the tree-structure sparsity-induced norm is used for learning the regression coefficients jointly to boost the performance of multi-class traffic sign recognition. Alternating direction method of multipliers (ADMM) is used to efficiently solve the proposed model with guaranteed convergence. Extensive experiments on public benchmark data sets demonstrate that the proposed algorithm leads to a quite interpretable model, and it has better or competitive performance with several state-of-the-art methods but with less computational and memory cost.

Unsupervised domain adaptation has attracted widespread attention as a promising method to solve the labeling difficulties of semantic segmentation tasks. It trains a segmentation network for unlabeled real target images using easily available labeled virtual source images. To improve performance, clustering is used to obtain domain-invariant feature representations. However, most clustering-based methods indiscriminately cluster all features mapped by category from both domains, causing the centroid shift and affecting the generation of discriminative features. We propose a novel clustering-based method that uses an adaptive refining-aggregation-separation framework, which learns the discriminative features by designing different adaptive schemes for different domains and features. The clustering does not require any tunable thresholds. To estimate more accurate domain-invariant centroids, we design different ways to guide the adaptive refinement of different domain features. A critic is proposed to directly evaluate the confidence of target features to solve the absence of target labels. We introduce a domain-balanced aggregation loss and two adaptive separation losses for distance and similarity respectively, which can discriminate clustering features by combining the refinement strategy to improve segmentation performance. Experimental results on GTA5→Cityscapes and SYNTHIA→Cityscapes benchmarks show that our method outperforms existing state-of-the-art methods.