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.

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.

To promote the progress of fault diagnosis system, this study proposes an intelligent and effective fault diagnosis algorithm based on data-driven. Firstly, we propose a new time-frequency analysis method named second-order time-reassigned multisynchrosqueezing transform (STMSST) based on Gaussian-modulated linear group delay (GLGD) model to deal with the vibration signals of fault object for obtaining time-frequency images with high resolution. Then, an improved training method named evenly mini-batch training method is combined with convolutional neural network (CNN) to train and learn fault features from those obtained time-frequency images. Further, the proposed fault diagnosis algorithm is tested on the Case Western Reserve University (CWRU) bearing dataset and the Machinery Failure Prevention Technology (MFPT) Society dataset, respectively, and the experimental results indicate that the feature representation and training effect in our method is superior to state-of-the-art fault diagnosis methods. Finally, the proposed method is applied on the loudspeaker pure-tone detection dataset, which achieves the loudspeaker anomaly diagnosis, and the diagnosis result has verified that the method can meet the needs of practical engineering.

Fault detection for key components in the braking system of freight trains is critical for ensuring railway transportation safety. Despite the frequently employed methods based on deep learning, these fault detectors are extremely reliant on hardware resources and complex to implement. In addition, no train fault detectors consider the drop in accuracy induced by scale variation of fault parts. This article proposes a lightweight anchor-free framework to solve the above problems. Specifically, to reduce the amount of computation and model size, we introduce a lightweight backbone and adopt an anchor-free method for localization and regression. To improve detection accuracy for multiscale parts, we design a feature pyramid network to generate rectangular layers of different sizes to map parts with similar aspect ratios. Experiments on four fault datasets show that our framework achieves 98.44% accuracy while the model size is only 22.5 MB, outperforming the state-of-the-art detectors.

To accurately diagnose fine‐grained fault of rolling bearing, this paper proposed a new fault diagnosis method combining multisynchrosqueezing transform (MSST) and sparse feature coding based on dictionary learning (SFC‐DL). Firstly, the high‐resolution time‐frequency images of raw vibration signals, including different kinds of fine‐grained faults of rolling bearing, were constructed by MSST. Then, the basis dictionary was trained through nonnegative matrix factorization with sparseness constraints (NMFSC), and the trained basis dictionary was employed to extract features from time‐frequency matrixes by using nonnegative linear equations. Finally, a linear support vector machine (LSVM) was trained with features of training samples, and the trained LSVM was employed to diagnosis the fault classification of test samples. Compared with state‐of‐the‐art fault diagnosis methods, the proposed method, which was tested on the bearing dataset from Case Western Reserve University (CWRU), achieved the fine‐grained classification of 10 mixed fault states. Meanwhile, the proposed method was applied on the dataset from the Machinery Failure Prevention Technology (MFPT) Society and realized the classification of 3 fault states under different working conditions. These results indicate that the proposed method has great robustness and could better meet the needs of practical engineering.

In this paper we design a fast fabric defect detection framework (Fast-DDF) based on gray histogram back-projection, which adopts end to end multi-convoluted network model to realize defect classification. First, the back-projection image is established through the gray histogram on fabric image, and the closing operation and adaptive threshold segmentation method are performed to screen the impurity information and extract the defect regions. Then, the defect images segmented by the Fast-DDF are marked and normalized into the multi-layer convolutional neural network for training. Finally, in order to solve the problem of difficult adjustment of network model parameters and long training time, some strategies such as batch normalization of samples and network fine tuning are proposed. The experimental results on the TILDA database show that our method can deal with various defect types of textile fabrics. The average detection accuracy with a higher rate of 96.12% in the database of five different defects, and the single image detection speed only needs 0.72s.