In line with the development of Industry 4.0, surface defect detection/anomaly detection becomes topical subject in industry field. Improving efficiency as well as saving labor costs has steadily become a matter of great concern in practice, where deep learning-based algorithms perform better than traditional vision inspection methods in recent years. While existing deep learning-based algorithms are biased towards supervised learning, which not only necessitates a huge amount of labeled data and human labor, but also brings about inefficiency and limitations. In contrast, recent research shows that unsupervised learning has great potential in tackling above disadvantages for visual industrial anomaly detection. In this survey, we summarize current challenges and provide a thorough overview of recently proposed unsupervised algorithms for visual industrial anomaly detection covering five categories, whose innovation points and frameworks are described in detail. Meanwhile, publicly available datasets for industrial anomaly detection are introduced. By comparing different classes of methods, the advantages and disadvantages of anomaly detection algorithms are summarized. Based on the current research framework, we point out the core issue that remains to be resolved and provide further improvement directions. Meanwhile based on the latest technological trends, we offer insights into future research directions. It is expected to assist both the research community and industry in developing a broader and cross-domain perspective.

Assistive devices for visually impaired people (VIP) which support daily traveling and improve social inclusion are developing fast. Most of them try to solve the problem of navigation or obstacle avoidance, and other works focus on helping VIP to recognize their surrounding objects. However, very few of them couple both capabilities (i.e., navigation and recognition). Aiming at the above needs, this paper presents a wearable assistive device that allows VIP to (i) navigate safely and quickly in unfamiliar environment, and (ii) to recognize the objects in both indoor and outdoor environments. The device consists of a consumer Red, Green, Blue and Depth (RGB-D) camera and an Inertial Measurement Unit (IMU), which are mounted on a pair of eyeglasses, and a smartphone. The device leverages the ground height continuity among adjacent image frames to segment the ground accurately and rapidly, and then search the moving direction according to the ground. A lightweight Convolutional Neural Network (CNN)-based object recognition system is developed and deployed on the smartphone to increase the perception ability of VIP and promote the navigation system. It can provide the semantic information of surroundings, such as the categories, locations, and orientations of objects. Human–machine interaction is performed through audio module (a beeping sound for obstacle alert, speech recognition for understanding the user commands, and speech synthesis for expressing semantic information of surroundings). We evaluated the performance of the proposed system through many experiments conducted in both indoor and outdoor scenarios, demonstrating the efficiency and safety of the proposed assistive system.

Automatic traffic accident detection has attracted the attention of the machine vision community for the rapid development of autonomous intelligent transportation systems (ITS). However, previous studies in this domain have been constrained by small-scale datasets with limited scope, impeding their effectiveness and applicability. Specifically, highway traffic accidents, often resulting in severe consequences due to higher speeds, require a more comprehensive approach to detection. The use of video surveillance provides a unique perspective, capturing the entire accident sequence. Unfortunately, existing traffic accident datasets are either not sourced from surveillance cameras, not publicly available, or not tailored for highway scenarios. An open-sourced traffic accident dataset with various scenes from surveillance cameras is in great need and of practical importance. To fulfill the above urgent need, we endeavor to collect abundant video data of real traffic accidents and propose a large-scale traffic accidents dataset, named TAD. Various experiments on image classification, video classification, and object detection tasks, using public mainstream vision algorithms or frameworks are conducted in this work to demonstrate the performance of different methods. The proposed dataset together with the experimental results are presented as a new benchmark to improve computer vision research, especially in ITS. The dataset is publicly available at https://github.com/yajunbaby/TAD-benchmark.

Road abandoned objects are potential safety hazards in modern traffic transport, especially in highway scenes. Promptly detecting such obstacles on the road is of great significance for driving safety and Intelligent Transportation Systems (ITS). Current research primarily focuses on developing diverse road anomaly detection approaches to discriminate the unknown objects regarded as abandoned ones. However, previous efforts have been largely inadequate due to the absence of abundant datasets. In addition, prevailing benchmarks mainly provide data pertinent to autonomous driving, which might not effectively generalize to highway scenarios owing to camera perspective and scope limitations. To address these challenges, we introduce a large-scale Road Abandoned Object Detection (RAOD) benchmark derived from video surveillance. First, we collect abundant real-world video clips containing various potential abandoned object categories on the road from our commercial ITS, then assemble a road abandoned object dataset comprising 557 video sequences and 18,953 images with pixel-level manual annotations. Second, we conduct exhaustive evaluation experiments employing a range of baseline models from mainstream algorithms on our dataset to illustrate the performance of different approaches. Third, we propose a novel image segmentation framework based on an area-aware attention mechanism. Experimental results reveal that our method outperforms the UNet-based model by nearly 9% in terms of dice score. Our dataset represents the most extensive open-source resource dedicated to road abandoned object detection, accessible publicly at https://github.com/yajunbaby/A-Benchmark-for-Road-Abandoned-Object-Detection-from-Video-Surveillance.