X-ray image plays an important role in manufacturing industry for quality assurance, because it can reflect the internal condition of weld region. However, the shape and scale of different defect types vary greatly, which makes it challenging for model to detect weld defects. In this article, we propose a weld defect detection method based on convolution neural network (CNN), namely, lighter and faster YOLO (LF-YOLO). In particular, a reinforced multiscale feature (RMF) module is designed to implement both parameter-based and parameter-free multiscale information extracting operations. RMF enables the extracted feature map to represent more plentiful information, which is achieved by a superior hierarchical fusion structure. To improve the performance of detection network, we propose an efficient feature extraction (EFE) module. EFE processes input data with extremely low consumption and improves the practicability of whole network in actual industry. Experimental results show that our weld defect detection network achieves satisfactory balance between performance and consumption and reaches 92.9 mean average precision (mAP50) with 61.5 frames/s. To further prove the ability of our method, we test it on the public dataset MS COCO, and the results show that our LF-YOLO has an outstanding versatility detection performance. The code is available at https://github.com/lmomoy/LF-YOLO .

Efficient RGB-D semantic segmentation has received considerable attention in mobile robots, which plays a vital role in analyzing and recognizing environmental information. According to previous studies, depth information can provide corresponding geometric relationships for objects and scenes, but actual depth data usually exist as noise. To avoid unfavorable effects on segmentation accuracy and computation, it is necessary to design an efficient framework to leverage cross-modal correlations and complementary cues. In this paper, we propose an efficient lightweight encoder-decoder network that reduces the computational parameters and guarantees the robustness of the algorithm. Working with channel and spatial fusion attention modules, our network effectively captures multi-level RGB-D features. A globally guided local affinity context module is proposed to obtain sufficient high-level context information. The decoder utilizes a lightweight residual unit that combines short- and long-distance information with a few redundant computations. Experimental results on NYUv2, SUN RGB-D, and Cityscapes datasets show that our method achieves a better trade-off among segmentation accuracy, inference time, and parameters than the state-of-the-art methods.

Real-time vision based system of fault detection (RVBS-FD) for freight trains aims to complete routine maintenance tasks efficiently for ensuring railway transportation security. However, most existing systems are designed to detect only one specific type of faults or even one fault, which fail to deal with multi-fault detection. Recently, the rapid development of deep learning techniques enables systems to provide a robust solution for the RVBS-FD of freight trains. But general convolutional neural networks (CNN) cannot fully meet the actual requirements in terms of the real-time, accuracy, and resource constrains for the RVBS-FD of freight trains. To solve these problems, we propose a CNN-based detector called Light FTI-FDet for the RVBS-FD of freight train. First, we use the multi-region proposal networks which extract a set of prior bounding boxes to achieve initial fault proposal generation. Then, a powerful multi-level region-of-interest pooling is presented for proposal classification and accurate detection. We finally design a reliable model reduction scheme to pursue fast speed with high detection accuracy in a simple manner. The experimental results on five typical fault benchmarks indicate that our Light FTI-FDet achieves higher accuracy and fast speed with about 17% model size of the well-known Faster R-CNN detector, substantially outperforming state-of-the-art methods.

Real-time fault detection for freight trains plays a vital role in guaranteeing the security and optimal operation of railway transportation under stringent resource requirements. Despite the promising results for deep-learning-based approaches, the performance of these fault detectors on freight train images is far from satisfactory in both accuracy and efficiency. This article proposes a unified light framework to improve detection accuracy while supporting a real-time operation with a low-resource requirement. We first design a novel lightweight backbone (real-time fault detection network-RFDNet) to improve the accuracy and reduce computational cost. Then, we propose a multiregion proposal network using multiscale feature maps generated from the RFDNet to improve the detection performance. Finally, we present multilevel position-sensitive score maps and region of interest pooling to further improve accuracy with few redundant computations. Extensive experimental results on public benchmark datasets suggest that our RFDNet can significantly improve the performance of the baseline network with higher accuracy and efficiency. Experiments on six fault datasets show that our method is capable of real-time detection at over 38 frames/s and achieves competitive accuracy and lower computation than the state-of-the-art detectors.

Image segmentation approaches have been utilized to determine the particle size distribution of crushed ores in the past decades. It is not possible to deploy large and high-powered computing equipment due to the complex working environment, so existing algorithms are difficult to apply in practical engineering. This article presents a novel efficient and lightweight framework for ore image segmentation to discern full and independent ores. First, a lightweight backbone is introduced for feature extraction while reducing computational complexity. Then, we propose a compact pyramid network to process the data obtained from the backbone to reduce unnecessary semantic information and computation. Finally, an optimized detection head is proposed to obtain the feature to maintain accuracy. Extensive experimental results demonstrate the effectiveness of our method, which achieves 40 frames per second on our new ore image dataset with a very small model size. Meanwhile, our method maintains a high level of accuracy—67.68% in $A{P}_{50}^{box}$ and 46.73% in $A{P}_{50}^{mask}$—compared with state-of-the-art approaches.