Occluded person re-identification (re-id) aims to match occluded person images to holistic ones. Most existing works focus on matching collective-visible body parts by discarding the occluded parts. However, only preserving the collective-visible body parts causes great semantic loss for occluded images, decreasing the confidence of feature matching. On the other hand, we observe that the holistic images can provide the missing semantic information for occluded images of the same identity. Thus, compensating the occluded image with its holistic counterpart has the potential for alleviating the above limitation. In this paper, we propose a novel Reasoning and Tuning Graph Attention Network (RTGAT), which learns complete person representations of occluded images by jointly reasoning the visibility of body parts and compensating the occluded parts for the semantic loss. Specifically, we self-mine the semantic correlation between part features and the global feature to reason the visibility scores of body parts. Then we introduce the visibility scores as the graph attention, which guides Graph Convolutional Network (GCN) to fuzzily suppress the noise of occluded part features and propagate the missing semantic information from the holistic image to the occluded image. We finally learn complete person representations of occluded images for effective feature matching. Experimental results on occluded benchmarks demonstrate the superiority of our method.

Unmanned aerial vehicles (UAVs) can conveniently capture the insulator images in aerial scenes. With the aerial insulator images, we can effectively conduct insulator status inspections. However, the insulator anomaly detection is challenging with low accuracy due to the complex background in insulator images as well as the insulator variety. To cope with this problem, we propose a novel insulator anomaly detection method. Specifically, we first use the Generative Adversarial Network (GAN) to coarsely detect insulator defects based on the reconstruction error of insulator area. Then, we incorporate the foreground attribute learning and structure attribute learning to dynamically improve our model’s sensitivity for detecting the insulator defects. The foreground attribute learning aims to highlight the foreground regions of aerial insulator images, which makes the image features more robust to the background interference. Also, by using the structure attribute learning method, our model can learn normal structure pattern of insulators more effectively, increasing the ability to distinguish the abnormal sample. With these strategies, the proposed model reduces the influence of background interference and becomes more discriminative to the insulator defects. Extensive experiments on one real-world UAV images dataset have demonstrated the effectiveness of the proposed method for insulator anomaly detection.

In large-scale power transmission stations, more and more automated pointer gauge reading algorithms are being used to automatically and efficiently take gauge readings. However, most existing pointer gauge reading algorithms do not take into account image deformation, changes of illumination, and small object interference in one algorithm, so these algorithms have poor robustness and adaptability to complex situations in real environments, and cannot obtain correct gauge readings consistently. In this paper, we present a pointer gauge adaptive reading method based on a double match. Our doublematch gauge reading method is dedicated to reading the gauge adaptively by using some strong anti-interference methods after image registration. To achieve this, various gauge images should first be registered by detection and matching of feature points using perspective transformation, and then pointer center positioning and gauge reading calculations are performed, based on matching multiple image moments. In the experimental results, compared with the classical gauge reading algorithm based on saliency and Hough line detection, our method shows better precision and better anti-interference; furthermore, the adaptability of the pointer gauge reading algorithm is effectively improved.

Hyperspectral anomaly detection (HAD) is of great value in both practical and theoretical terms. However, due to the lack of available semantic labels, previous works mainly relied on unsupervised or semi-supervised methods to construct learning models, which inevitably lacked semantic guidance and led to limited anomaly detection (AD) effectiveness. Besides, few previous methods jointly mine spectral and spatial global dependencies, which limits their effectiveness in practical scenarios. To address the above problems, we design a novel self-supervised HAD method, named the Self-Supervised Hyperspectral Anomaly Detection method based on the Finite Spatial-wise Attention. The core of proposed method is the designed Self-Supervised Hyperspectral Anomaly Detection transFormer (SSHADFormer). It explores the specific spectral attributes of hyperspectral images (HSIs) to reconstruct background HSI from a given RGB image, which solves the difficulty of acquiring semantic information and enhances the agility of AD models. In addition, we propose a Finite Spatial-wise Attention mechanism. The mechanism mines the cluster structure of the background spectrum in a data-driven manner, enhancing the discriminative ability between background and anomalous targets while avoiding anomalous targets interference during training. Extensive experiments on six public datasets demonstrate the effectiveness and agility of the proposed method.

Through Global Navigation Satellite System (GNSS) occultation measurement, the global ionosphere and atmosphere can be observed. When the navigation satellites’ signal passes through the lower atmosphere, the rapid change of the atmospheric refractive index gradient will cause serious multipath phenomena in radio wave propagation. Atmospheric doppler frequency shift and amplitude signal fluctuations increase drastically. Due to the attenuation of signal amplitude and the rapid change of the Doppler frequency, the general phase locked loop (PLL) cannot work properly. Hence, a more stable tracking technology is needed to track the occultation signal passing through the lower atmosphere. In this paper, a mountain-top based radio occultation experiment is performed, where we employ an open-loop receiver and remove the navigation bits by the internal demodulation. In the process of the experiment, we adopt the open-loop tracking technique and there is no feedback between the observed signal and the control model. Specifically, taking the pseudo-range and doppler information from models as input, three key parameters, i.e., accurate code phase, carrier doppler and code doppler, can be obtained, and furthermore, the accurate accumulation is determined by them. For the full open-loop occultation data, a closed-loop observation assisted strategy is presented to compare the tracking results between open-loop and closed-loop occultation data. Through the compared results, we can determine whether the initial phase has been reversed or not, and obtain the high consistency corrected open-loop data that can be directly used for subsequent atmospheric parameters inversion. To verify the effect of open-loop tracking and open-loop inversion, we used the company’s self-developed occult receiver system for verification. The company’s self-developed occult receiver system supports Global Position System (GPS)/Beidou satellites constellation (BD, the 2nd and 3rd generations) dual systems. We have verified GPS and BD open-loop tracking and inversion, carried out in a three-week mountain-based experiment. We used closed-loop and open-loop strategies to track and capture the same navigation star to detect its acquisition effect. Finally, we counted the results of a week (we only listed the GPS data; BD’s effect is similar). The experimental results show that the open-loop has expanded the signal-cut-off angle by nearly 20% under the condition of counting all angles, while the open-loop has increased the signal-cut-off angle value by nearly 89% when only calculating the negative angle. Finally, the atmosphere profiles retrieved from observations in open-loop tracking mode are evaluated with the local observations of temperature, humidity and pressure provided by the Beijing Meteorological Bureau, and it is concluded that the error of open-loop tracking method is within ~4% in MSER (mean square error of relative error), which meets the accuracy of its applications (<5%, in MSER).