Infrared dim and small target detection is one of the crucial technologies in the military field, but it faces various challenges such as weak features and small target scales. To overcome these challenges, this paper proposes IR-TransDet, which integrates the benefits of the convolutional neural network and the Transformer to properly extract global semantic information and features of small targets. First, the Efficient Feature Extract Module (EFEM) is designed, which uses depthwise convolution and pointwise convolution to effectively capture the features of the target. Then, an improved Residual Sim Atrous Spatial Pyramid Pooling (ASPP) module is proposed based on the image characteristics of infrared dim and small targets. The proposed method focuses on enhancing the edge information of the target. Meanwhile, an IR-Transformer module is devised, which uses the self-attention mechanism to investigate the relationship between the global image, the target, and neighboring pixels. Finally, experiments were conducted on four open datasets, and the results indicate that IR-TransDet achieves state-of-the-art performance in infrared dim and small target detection. To achieve a comparative evaluation of the existing infrared dim and small target detection methods, this study constructed the ISTD-Benchmark tool, which is available at https://linaom1214.github.io/ISTD-Benchmark.

This paper proposes the feature extraction backbone network MNET that is specifically designed for the detection of infrared small targets. The overall network uses three down-sampling operations to adjust the size of the feature map, while preserving sufficient physical characteristics of the small infrared target to be used in the detection. In a next step, the dense connection is used to save the output of each layer of the network in the front channel of the feature map, to better integrate the location information of the shallow network and the semantic information of the deep network. In this way accurate network positioning and classification effects are achieved. As a last step, we introduce a feature attention mechanism to obtain the importance of each feature channel, and to enhance useful features according to their degree of importance. In this way we achieve an adaptive calibration of the feature channels. In order to train the proposed detection network MNET from scratch, the single-phase detection algorithm YOLO is adopted for the detection part. To verify the effectiveness of the proposed method, we captured images and created an infrared small target dataset. The experimental results show that MNET can accurately detect targets of 2×2 pixels size in infrared images of 640×512 pixels at a processing speed of up to 105 frames per second. MNET meets real-time requirements while providing high quality detection accuracy.

Wireless sensor network (WSN) is an emerging technology with a wide range of potential applications in smart buildings. The measuring process by using WSNs in the actual environment always introduces noise, errors, accidents, and other potential outliers to the data collected by the sensors. It is crucial to establish an effective approach for outlier detection and recovery in the real applications of WSNs. In this paper, we propose an outlier detection and recovery approach using artificial neural network (ANN), which can be used to determine whether the temperature values measured by the sensors in WSNs are outliers. The experimental results in real building show that the proposed ANN-based models can provide a reasonably good prediction of the temperature and high accuracy in buildings compared with the hidden Markov model (HMM)-based approach, which can potentially be used for outlier detecting and thermal controlling in the Internet of Things (IoT) applications.

Infrared small target detection under complex background is of great significance in the field of remote sensing, such as optical remote sensing, infrared precise guidance, infrared surveillance, and night navigation. Because of low-contrast and complex-background clutters of infrared images, infrared small target detection under complex background is difficult and has a serious false alarm. In this paper, a difference-based local contrast method is proposed to improve the detection performance. First, a median filtering process is used to reduce pixel-sized noises, and infrared image after filtering is divided into a series of sub-images. Then, a difference-based local contrast measure based on contrast mechanism is calculated for generating the saliency map, which can exceedingly improve the detection rate and reduce the false alarm rate. Eventually, an adaptive threshold is used to extract the target sub-image. Experiments on five real infrared small target image datasets show that the proposed method is robust and effective with great respect to detection accuracy. Our method can achieve a higher detection rate and lower false alarm rate under complex background with better performance in target enhancement and background suppression compared with the traditional algorithms.