星空背景下空间目标的快速识别与精密定位

For the linear array scanning infrared detection system, the reasonable design of the system hardware architecture and data processing flow is the key to ensure the system to achieve real-time target detection and fast recognition. Fast and effective target recognition algorithm is the core of the system design. The signal processing of the linear scanning infrared detection system designed in this paper adopts the hardware architecture of FPGA + DSP + GPU, and puts forward the false target discrimination method of sky and earth line based on semantic segmentation based on deep learning, which is different from the traditional threshold detection and segmentation method based on artificial template matching. The deep learning method uses the semantic information and spatial information of infrared image and has certain adaptability. Finally, the algorithm is implemented on the hardware system through the field measured data, and the effectiveness of the algorithm is verified.

The location and intensity of non-resolved space object can be obtained in space-based surveillance, however, the material, size, and status of the object are lost. Spectrum represents the inherent property difference of the object, which can be used as an important means for feature extraction and recognition of non-resolved space object. According to the influence factors, including material, structure, background and orbit, a mathematical model for spectral properties of space object is established. Based on the model, inverse calculation method for feature extraction and recognition of space object is proposed. Taking the HuanJing-1 satellite scale model as an example, experimental verification for feature extraction and recognition of space object in typical parameters is made. Experimental results demonstrate the validity of the modeling method.

Fire will cause great loss to life, property and ecological environment. The key to reduce the loss of fire is to send out fire warning quickly. Based on the requirement of real-time flame recognition of embedded video monitoring equipment, this paper proposes a fast flame recognition algorithm based on tracking and marking. First, the improved color model of flame is used to complete the segmentation of candidate regions. Then neural network is used to give the final classification results. The core idea of the proposed algorithm is to replace the process of classification with the process of tracking and marking, for the reason that the time consuming of classification through neural network is much longer than that of tracking and marking and the number of calls of neural network can reduce in the proposed algorithm. Comparing the proposed algorithm with other flame recognition algorithms in recent years, it can not only keep the high accuracy of classification, but also shorten the execution time of the algorithm.

In this paper, we propose a new algorithm combined with the existing object recognition algorithm. Multi-object recognition algorithms are now various, with their respective advantages and disadvantages according to their uses. However, these algorithms can only detect and recognize objects without being able to know the location of the object relative to the sensor. The ability to know the location of the object is needed so that the autonomous car can make the right decisions without harming the driver. Since it requires fast and precise object detection and recognition capabilities, the algorithm used in object recognition is YOLOv4 with CSPDarknet-53. And because object recognition uses a neural network, the algorithm in determining the location of the object needs to be made as efficient as possible without affecting the performance of the object recognition algorithm, so that the mapping algorithm is used. The YOLOv4 model used has a precision value of 57.23 percent with a detection capability of 0.03785 seconds without a mapping algorithm, and if it is added with a mapping algorithm, the detection time becomes 0.03792 seconds. Since it has fast detection time, thus it can be applied to a real-time application.

Image quality detection technology can replace manual inspections to automatically detect video quality, accurately analyze, judge and alarm abnormalities in video images in the surveillance system to ensure the normal operation of the expanding network video surveillance system. The thesis designs an intelligent traffic image sensor system to realize fast motion detection and object recognition of the surveillance scene. This system introduces a background model based on region segmentation and a feature-based object recognition algorithm. Experimental results show that the system can perform automatic movement detection and object classification and recognition efficiently in real time.

Fast control chart pattern recognition aids in instantaneous detection of abnormal functioning of a system. In this paper, we present a parallel algorithm for fast control chart pattern recognition. It addresses three major issues of control chart pattern recognition: (i) transparency (ii) accuracy and (iii) fast detection of abnormal patterns. The algorithm uses novel shape features extracted from a control chart pattern (CCP) instead of the unprocessed CCP data or its statistical properties. These shape features can be extracted in parallel. A parallel algorithm that is based on distributed and synergistic neural network structure for recognition of CCPs is described. The paper presents the results of analyzing several hundred control chart patterns and gives a comparison with those reported in previous work.

Both man-made and natural objects are described by both their geometric shapes and by their non-geometric attributes such as color. The objective of the proposed research is to create a system which integrates geometric and non-geometric attribute information for fast 3D model-based object recognition. Hashing is employed in a hypothesize and verify approach to the 3D model-based object recognition problem. Viewpoint independent attributes are used in the hypothesis generation stage to eliminate model objects from consideration during hypothesis formation. Utilizing more than one attribute in the proposed hashing scheme helps to ensure a reduction in the actual execution time for object recognition over a larger number of model bases. A nice feature of the system is that new object attributes can be added with relative ease. Issues concerning the ranking of attributes by their distinctiveness with respect to the objects in the model base are discussed. Current work on the use of an information theoretic measure in the design of an optimal multiple attribute hash table is presented.

Single-unit recordings demonstrated that the adult mammalian visual cortex is capable of reorganizing after induced retinal lesions. In humans, whether the adult cortex is capable of reorganizing has only been studied using functional magnetic resonance imaging, with equivocal results. Here, we exploited the phenomenon of visual crowding, a major limitation on object recognition, to show that, in humans with long-standing retinal (macular) lesions that afflict the fovea and thus use their peripheral vision exclusively, the signature properties of crowding are distinctly different from those of the normal periphery. Crowding refers to the inability to recognize objects when the object spacing is smaller than the critical spacing. Critical spacing depends only on the retinal location of the object, scales linearly with its distance from the fovea, and is approximately two times larger in the radial than the tangential direction with respect to the fovea, thus demonstrating the signature radial-tangential anisotropy of the crowding zone. Using retinal imaging combined with behavioral measurements, we mapped out the crowding zone at the precise peripheral retinal locations adopted by individuals with macular lesions as the new visual reference loci. At these loci, the critical spacings are substantially smaller along the radial direction than expected based on the normal periphery, resulting in a lower scaling of critical spacing with the eccentricity of the peripheral locus and a loss in the signature radial-tangential anisotropy of the crowding zone. These results imply a fundamental difference in the substrate of cortical processing in object recognition following long-term adaptation to macular lesions.

As we move through our environment, we encounter familiar objects from various viewpoints. Despite the ensuing variability of the images projected onto the retina, we have seemingly little difficulty when it comes to recognizing objects we encounter. We can, however, see how the objects are oriented, suggesting that object recognition is to a certain degree dissociable from perception of other object “features” such as orientation. Changes in orientation of objects, particularly inversion, can also affect how we perceive the objects. A particularly illustrative example (shown in Figure ​Figure1)1) is that of the Thatcher illusion (Thompson, 1980), where the grotesque appearance of a face with its inverted eyes and mouth is “hidden” when the whole face is also inverted. The percept itself, therefore, is affected by the change in orientation. In addition, there are also subtle effects of viewpoint changes on object recognition itself. For example, identifying rotated objects is more difficult when they are briefly presented than when viewing time is unlimited (Lawson and Jolicoeur, 2003), and identifying a face is considerably more difficult the face has been inverted (Yin, 1969), as is discrimination between characters “b” and “d,” or “p” and “q” which requires (physical or mental) rotation of the characters to upright, before we can be certain which letter we are looking at (Corballis and McLaren, 1984). Figure 1 Unaltered and “thatcherized” version of Margaret Thatcher's face. The grotesque appearance of the face when its eyes and mouth are inverted is hidden by the inversion of the whole image. Rotating the pictures to upright makes discrimination ... These subtle, yet persistent, effects of viewpoint changes on perception and recognition arise as a consequence of how visual object processing is handled by the brain. Here, I discuss how neural mechanisms underlying visual processing give rise to perception and recognition which can be both viewpoint dependent and viewpoint invariant depending on the timing of those processes, as well as specific task demands or current “perceptual goals” of an individual. To do so, I will firstly explain how temporal dynamics of low-level visual processing may give rise to impaired recognition at short viewing latencies and suggest that this may also relate to effects of viewpoint changes on perceptual experience. I will then discuss how the perceptual goals of an individual determines whether recognition is accomplished in viewpoint invariant or dependent manner with a particular focus on cognitive operations thought to be subserved by ventral and dorsal visual streams, namely object recognition and mental rotation, respectively.

The role of invariant line junctions in object and visual word recognition

Object recognition from depth sensors has recently emerged as a renowned and challenging research topic. The current systems often require large amounts of time to train the models and to classify new data. In this work, we present a novel fast approach for object recognition from 3D data acquired from depth sensors such as Structure or Kinect sensors. We first extract simple but effective frame-level features from the raw depth data and build a recognition system based on extreme learning machine with a local receptive field. We test the presented method on two datasets: A self-collected dataset and the benchmark RGB-D object dataset. Experiments on both datasets show the effectiveness of our presented approach compared with the state-of-the-art methods. Fast computational time and high recognition accuracy make the presented method readily applicable for online recognition applications.

We present in this paper a real-time method for visual categorization to do robot grasping. We describe an object database with SURF feature points which we quantify with the Kmeans clustering algorithm to make visual words. Then, we train a Support Vector Machine classifier having as entries the distribution of the bag of features extracted earlier. Likewise, we do object recognition using the SVM algorithm. The real-time implementation is done with the OpenCV GPU. The application aims to pick up an object and drop it using our robot manipulator equipped with a camera using our visual system. Finally, the results of our experiments of the object recognition show an average of recognition between 95% and 100%.

Relevance: With the growing need for fast and accurate real-time object recognition, especially for mobile and embedded systems, the question of choosing the optimal AI models arises. Comparisons of lightweight and high-precision architectures such as YOLOv5 and MobileNetV3 are important for developing efficient computer vision systems and exploring the principles of hybrid model construction. Purpose: Comparison of the YOLOv5 and MobileNetV3 architectures to analyze the efficiency for real-time object recognition applications, and to confirm that hybrid models can improve the efficiency of these tasks. Research methods: image preprocessing methods, deep neural network training methods, measurement of accuracy, processing speed, and resource usage; comparative analysis of results to assess model effectiveness. Results: An experimental study showed that YOLOv5 demonstrates better overall accuracy on the COCO test suite, but requires more computing resources. MobileNetV3, on the other hand, provides faster output and efficient functioning on low-power devices, sacrificing accuracy in part. As such, both models have proven their suitability for real-world applications, and the choice between them depends on the specific balance between speed, accuracy, and platform limitations. Combining these models gives better results in object recognition, although this may increase the size of the model itself and resource consumption. Conclusions: As a result of the study, the YOLOv5, MobileNetV3 and hybrid models for the object recognition problem were compared. The hybrid model demonstrated better accuracy and balance between processing speed and resource utilization than individual models. This indicates the feasibility of using hybrid approaches to improve the efficiency of computer vision systems in real conditions. Therefore, the hybrid model is a promising direction for further research and practical implementation.

<p indent="0mm">Imaging characteristics of stars and artificial targets in space are very similar in long-distance space-based observation as they are both light spots described by point spread function with a Gaussian distribution. In the condition of low signal-to-noise ratio, the signal of space artificial targets is faint on the image, which is covered with background and noise signals; thus, it is more difficult to recognize the faint space artificial targets from complex backgrounds. To solve this problem, this paper proposes a fast recognition algorithm for faint targets on the basis of matched filters. First, the imaging model of space artificial targets is built in the star tracking observation mode, wherein space artificial targets and stars appear as streaks and points, respectively. Therefore, the faint point target recognition problem is transferred to faint streak pattern recognition from light spot background. Second, the signal-to-noise ratio is used to define the faint degree of targets to evaluate the recognition limit of the algorithm. Then, a streak element pattern is designed. It is a part of the whole streak pattern; thus, the generation of streak patterns with varying lengths in the progress of matched filter can be avoided, so the calculation is decreased and the recognition speed is increased. Finally, to verify the fast recognition algorithm of faint targets, several images with stars and faint space artificial targets under different signal-to-noise ratios are simulated. The fast recognition algorithm of faint targets is tested using these simulation images; the results reveal that faint targets can be recognized from simulation images using this algorithm when the signal-to-noise ratio is above 0.5.

This paper describes a voting-based approach for the fast automatic recognition of man-made objects and related attitude estimation in underwater acoustic images generated by forward-looking sonars or acoustic cameras. In general, the continuous analysis of sequences of images is a very heavy task for human operators and this is due to the poor quality of acoustic images. Hence, algorithms able to recognize an object on the basis of a priori knowledge of the model and to estimate its attitude with reference to a global coordinate system are very useful to facilitate underwater operations like object manipulation or vehicle navigation. The proposed method is capable of recognizing objects and estimating their two-dimensional attitude by using information coming from boundary segments and their angular relations. It is based on a simple voting approach directly applied to the edge discontinuities of underwater acoustic images, whose quality is usually affected by some undesired effects such as object blurring, speckle noise, and geometrical distortions degrading the edge detection. The voting approach is robust, with respect to these effects, so that good results are obtained even with images of very poor quality. The sequences of simulated and real acoustic images are presented in order to test the validity of the proposed method in terms of average estimation error and computational load.