Subsequent Target Detection Research Articles

UniverDetect: Universal landmark detection method for multidomain X-ray images

Landmark detection using X-ray imaging is vital for disease screening, treatment, and prognosis. It provides a framework for subsequent tasks, including segmentation, classification, and target detection. Existing landmark detection methods exhibit limits with the increasing number of X-ray examiners. Not only they serve specific data types, but also their ability to learn the complete semantic information from this dataset is limited, potentially affecting their widespread adoption. We address these challenges by proposing a universal landmark detection model for multidomain X-ray imaging, UniverDetect. By progressively acquiring local semantic information, global semantic insights, and anatomical structure knowledge at various levels, the model ensured that the detected landmarks were closely aligned with the ground-truth labels. UniverDetect consists of three key components. The landmark detection module (LDM) utilizes a U-net network equipped with our innovative pyramid depthwise separable (PDS) convolution module for initial landmark detection. The landmark refinement module (LRM) integrates a fine-tuning module comprising continuously extended convolution blocks. Finally, the landmark correction module (LCM) incorporates a graph convolutional network (GCN) to rectify offset errors during partial landmark detection. An inherent feature of this model is its domain- generalization capability, which enables continuous learning across diverse domains. This model can concurrently learn from eight domains, covering 118 landmarks within a diverse dataset of 5969 images. Extensive experiments on multiple datasets demonstrate that this method consistently outperforms state-of-the-art approaches. This study presents a versatile and effective solution to reduce doctors’ workload while providing precise quantitative analysis.

Tiny drone object detection in videos guided by the bio-inspired magnocellular computation model

Detecting drones in infrared videos is highly desired in many realistic scenarios, e.g., unauthorized drone monitoring around airports. Nevertheless, automated drone detection is rather challenging when the targets appear as tiny objects (≤10×10 pixels) against complex backgrounds. Conventional object detection algorithms, which mainly use static visual features, can hardly distinguish tiny objects from undesired artefacts in complex backgrounds. To alleviate this problem, we learn from the early biological visual pathway (including the parvocellular and magnocellular pathways), which process static and motion information simultaneously. Therefore, we propose a magnocellular inspired method for video tiny-object detection (Magno-VTOD) that integrates both static and motion visual information. The Magno-VTOD firstly employs a retinal magnocellular computation model to extract the motion strength of moving objects. The motion responses are then used to enhance the areas of the flying tiny drones effectively and efficiently, thereby facilitating the subsequent target detection procedure. We implement the video tiny-object detection method based on the widely adopted deep neural networks guided by the magnocellular computation model. Experimental results obtained on the large-scale Anti-UAV dataset (304451 video frames) validate that the proposed Magno-VTOD method significantly outperforms the competing state-of-the-art object detection methods on the tiny drone detection task. Particularly, the AP value is increased by 15.4% for tiny object detection, and by 17.1%/13.7% against wood/mountain backgrounds.

Deep learning based multi-target detection for roads

The vehicle target detection algorithm based on deep learning has gradually become a research hotspot in this field. In recent years, with the significant breakthrough of deep learning in the field of target recognition, the vehicle target detection algorithm based on deep learning has gradually become a research hotspot in this field. For the task of vehicle target detection, this paper first briefly introduces the process of traditional target detection algorithms and some optimization methods. It summarizes the development process of YOLO, the current mainstream one-stage vehicle target detection algorithm, and the process of Faster R-CNN, the second-stage vehicle target detection algorithm, and its improvement. Then the characteristics of several types of representative convolutional neural network algorithms are analyzed in chronological development order. Finally, it looks forward to t he future research direction of vehicle target detection algorithms, and also provides new ideas for the optimization of the subsequent vehicle target detection algorithms, which have good engineering application value. Provides algorithmic support for the underlying logic of autonomous driving.

Willed Attentional Selection of Visual Features: An EEG Study.

Visual selective attention studies generally tend to apply cuing paradigms to instructively direct observers' attention to certain locations, features or objects. However, in real situations, attention in humans often flows spontaneously without any specific instructions. Recently, a concept named "willed attention" was raised in visuospatial attention, in which participants are free to make volitional attention decisions. Several ERP components during willed attention were found, along with a perspective that ongoing alpha activity may bias the subsequent attentional choice. However, it remains unclear whether similar neural mechanisms exist in feature- or object-based willed attention. Here, we included choice cues and instruct cues in a feature-based selective attention paradigm, allowing participants to freely choose or to be instructed to attend a color for the subsequent target detection task. Pre-cue ongoing alpha oscillations, cue-evoked potentials and target-related steady-state visual evoked potentials (SSVEPs) were simultaneously measured as markers of attentional processing. As expected, SSVEP responses were similarly modulated by attention between choice and instruct cue trials. Similar to the case of spatial attention, a willed-attention component (Willed Attention Component, WAC) was isolated during the cue-related choice period by comparing choice and instruct cues. However, pre-cue ongoing alpha oscillations did not predict the color choice (yellow vs blue), as indicated by the chance level decoding accuracy (50%). Overall, our results revealed both similarities and differences between spatial and feature-based willed attention, and thus extended the understanding toward the neural mechanisms of volitional attention.

Improved Retinex algorithm for low illumination image enhancement in the chemical plant area

Due to the complexity of the chemical plant area at night and the harsh lighting environment, the images obtained by monitoring equipment have issues such as blurred details and insufficient contrast, which is not conducive to the subsequent target detection work. A low illumination image enhancement model based on an improved Retinex algorithm is proposed to address the above issues. The model consists of a decomposition network, an adjustment network, and a reconstruction network. In the decomposition network, a new decomposition network USD-Net is established based on U-Net, which decomposes the original image into illumination and reflection maps, enhancing the extraction of image details and low-frequency information; Using an adjustment network to enhance the decomposed lighting image, and introducing a Mobilenetv3 lightweight network and residual structure to simplify the network model and improve the contrast of the image; In the reconstruction network, the BM3D method is used for image denoising to enhance the ability to restore image detail features; The enhanced illumination and reflection images were fused based on the Retinex algorithm to achieve low illumination image enhancement in the chemical plant area. This article uses five image quality evaluation indicators, namely Peak Signal-to-Noise Ratio, Structural Similarity Index, Natural Image Quality Evaluator, Interpolation Error, and Level of Effort, to compare eight traditional or modern algorithms and evaluate three different types of datasets. The experimental results show that the improved algorithm enhances the texture details of the image, improves the contrast and saturation of the image, and has good stability and robustness, which can effectively meet the needs of low illumination image enhancement in chemical plant areas.

Adaptive high-gray image enhancement algorithm based on logarithmic mapping and simulated exposure

In the fields of industry, security, military and other areas, high gray-level low contrast images have been widely used. However, due to the large dynamic range of gray level, high noise, blurry detail information and low contrast, it brings difficulties to subsequent image enhancement, target detection and other processes. Ordinary image enhancement algorithms are only suitable for conventional 8-bit images, which are not effective to deal with high-gray and low-contrast images. To address these issues, this paper proposed an adaptive high-gray image enhancement algorithm based on logarithmic mapping and simulated exposure, which was used for processing X-ray film images, infrared images, SAR images and other high gray-level low contrast images. Firstly, a detailed algorithm model construction method was provided for high gray-level low contrast images. Secondly, in order to verify the universality of the algorithm proposed in this paper, qualitative and quantitative experimental analyses were carried out using X-ray film images, infrared images and SAR images respectively. Finally, taking the most complex infrared image in the application environment as an example, the images, enhanced by the algorithm proposed in this paper, were sent to the YOLOv8 neural network for target detection, which improved the detection accuracy. The experiment shows that the algorithm, proposed in this paper, can significantly improve the image quality of high gray-level low contrast images, the detail information is obvious and the contrast is significantly improved. Various indicators are far higher than those of traditional algorithms. At the same time, this algorithm can provide reliable technical support for applications, such as target detection and target tracking in this field.

A spawning particle filter for defocused moving target detection in GNSS-based passive radar

Global Navigation Satellite System (GNSS)-based passive radar (GBPR) has been widely used in remote sensing applications. However, for moving target detection (MTD), the quadratic phase error (QPE) introduced by the non-cooperative target motion is usually difficult to be compensated, as the low power level of the GBPR echo signal renders the estimation of the Doppler rate less effective. Consequently, the moving target in GBPR image is usually defocused, which aggravates the difficulty of target detection even further. In this paper, a spawning particle filter (SPF) is proposed for defocused MTD. Firstly, the measurement model and the likelihood ratio function (LRF) of the defocused point-like target image are deduced. Then, a spawning particle set is generated for subsequent target detection, with reference to traditional particles in particle filter (PF) as their parent. After that, based on the PF estimator, the SPF algorithm and its sequential Monte Carlo (SMC) implementation are proposed with a novel amplitude estimation method to decrease the target state dimension. Finally, the effectiveness of the proposed SPF is demonstrated by numerical simulations and preliminary experimental results, showing that the target range and Doppler can be estimated accurately.

Frontocentral EEG activity phase predicts subsequent visual target detection in healthy participants but not in schizophrenia

Frontocentral EEG activity phase predicts subsequent visual target detection in healthy participants but not in schizophrenia

CRISPR Cas12a-mediated amplification-free digital DNA assay improves the diagnosis and surveillance of Nasopharyngeal carcinoma

Sensitive and accurate cell-free plasma Epstein-Barr virus (EBV) DNA measurement is essential in the routine diagnosis, monitoring and treatment of Nasopharyngeal Carcinoma (NPC). This measurement in commercial and in-house assay are commonly based on real-time quantitative PCR (qPCR) method, which requires reference materials for standardization and lack quantitative precision due to amplification bias or cross-contamination. To address these issues, we developed a CRISPR/Cas12a-mediated amplification-free digital DNA assay, which targets the repetitive sequences of EBV DNA and utilizes the cis-cleavage activity of CRISPR-Cas12a prior to droplet generation. By this mean, more activated Cas12a-crRNA duplexes could be produced for subsequent target detection and counting, thus improving the performance in detecting low EBV DNA load. We demonstrated that it was more robust than conventional qPCR for detecting plasma EBV DNA in a case-control study of 208 participants, especially when the target concentrations were around the diagnostic cut-off value for NPC. More importantly, this assay allowed a more accurate diagnosis of early-stage NPC, with an area under the curve (AUC) of 0.9883 (versus 0.7682 for qPCR). Furthermore, its absolute quantification capability enabled dynamic monitoring of EBV load in NPC patients during initial diagnosis, treatment, and recurrence, thereby potentially improving disease management and prognosis. Taken together, our results demonstrate that this amplification-free digital assay has the potential to be a robust tool to improve the diagnosis and surveillance of NPC.

Development of feature extraction method based on interval-valued Pythagorean fuzzy decision theory

Feature extraction is an important step in image processing and the accuracy of the extraction affects the result of subsequent target detection. There are many feature extraction algorithms, but there are few theories and methods about the accuracy of the extraction. Moreover, most of the existing extraction methods are computationally complex, and they will expose deficiencies once they encounter a large number of standard cases. In order to fill this gap, this study proposes a new soft computing multi-criteria group decision-making (MCGDM) method based on interval-valued Pythagorean fuzzy set information to deal with situations where multiple criteria are involved in complex decisions. Thus, the power average operator is used to eliminate the effects of unreasonable input arguments on decision-making results, and the Maclaurin symmetric mean operator is used to comprehensively consider the mutual relationship between input arguments in this article. Combining with the concept of IVPFS, the interval-valued Pythagorean fuzzy power Maclaurin symmetric mean (IVPFPMSM) operator and weighted IVPFPMSM operator are proposed. Then, the TOPSIS method is used to determine the weight vector of decision-making set, and a MCGDM method is developed under the interval-valued Pythagorean fuzzy framework. Next, aiming at the defects of the existing evaluation criteria, we consider the different ranges of membership degree and non-membership degree to propose a new evaluation criterion of MCGDM method. Finally, the proposed method is applied to the optimal selection of characteristic interval of foreign fibers to verify its practicability and effectiveness. The proposed method has certain guiding significance for the extension of decision-making fuzzy operators and the exploration of feature extraction methods.

Interacting rhythms enhance sensitivity of target detection in a fronto-parietal computational model of visual attention.

Even during sustained attention, enhanced processing of attended stimuli waxes and wanes rhythmically, with periods of enhanced and relatively diminished visual processing (and subsequent target detection) alternating at 4 or 8 Hz in a sustained visual attention task. These alternating attentional states occur alongside alternating dynamical states, in which lateral intraparietal cortex (LIP), the frontal eye field (FEF), and the mediodorsal pulvinar (mdPul) exhibit different activity and functional connectivity at α, β, and γ frequencies-rhythms associated with visual processing, working memory, and motor suppression. To assess whether and how these multiple interacting rhythms contribute to periodicity in attention, we propose a detailed computational model of FEF and LIP. When driven by θ-rhythmic inputs simulating experimentally-observed mdPul activity, this model reproduced the rhythmic dynamics and behavioral consequences of observed attentional states, revealing that the frequencies and mechanisms of the observed rhythms allow for peak sensitivity in visual target detection while maintaining functional flexibility.

Scheme to implement moving target detection of coastal defense radar in complicated sea conditions

Although the data on a particular complicated sea conditions are available, it is difficult to collect the data on various complicated sea conditions simultaneously. When the sea conditions change, the test results of the detection network based on the data of simple sea conditions may be unacceptable. It is proposed that the VGG16, pix2pixHD, and cycleGAN methods should be applied to establish related datasets of different complicated sea conditions. After the unified image quality assessment indicators are determined, it is found that the images generated by the VGG16 network are most in line with the subsequent target detection standards. The real images of complicated sea conditions have the smallest root-mean-square error, the largest peak signal-to-noise ratio, and the best regression coefficient (R2). Meanwhile, the improved Faster R-CNN is introduced for target detection of small sample datasets. First, the ResNet50_FPN module, as the backbone feature extractor, is used to improve the detection performance of small-sized objects. Moreover, because there are many small target objects to be detected, the ROI Align module is preferred, for it is more accurate. Finally, the Softer-NMS algorithm is selected to significantly improve the positioning accuracy through confidence estimation. Compared with some previous Faster R-CNN methods, the accuracy and missed detection rate of the proposed method outperform other networks, with a mean average precision of 85.11%.

Infrared and visible image fusion based on contrast enhancement guided filter and infrared feature decomposition

Infrared (IR) and visible (VIS) images represent the features of the scene at different wavelengths, and the features they contain have different properties. Therefore, the traditional weighted fusion strategy is challenging to preserve the different types of feature information. In addition, VIS images are highly susceptible to bad weather, which also seriously affects the quality of fused images in complex environments. To solve the above problems, we propose a feature enhancement fusion method. First, a fusion model called contrast enhancement guided filter (CEGF) is proposed. The new model enables the texture information of VIS images to be presented with the intensity of infrared pixels, which solves the problem of combining different attribute features and removes the influence of harsh lighting conditions. To improve the visibility of texture details under different lighting conditions, a contrast modulation factor is added to the cost function design of the filter to enhance the contrast of visible details. Second, we use a dual-scale decomposition strategy to enhance the infrared feature information of the fusion results. Finally, we apply the method of this paper with ten classical image fusion algorithms in two types of datasets. The visual effect and objective evaluation of the fusion results verify that the proposed method preserves the characteristics of the high contrast of IR images and improves the visibility of infrared scenes for subsequent target identification and detection.

GPR Image Recovery Effect on Faster R-CNN-Based Buried Target Detection

Measurements acquired through ground-penetrating radar (GPR) may contain missing information that needs to be recovered before the implementation of any post-processing method, such as target detection, since buried target detection methods fail and cannot produce desired results if the input GPR image contains missing information. This study proves that the recovery of missing information in a GPR image has a direct influence on the performance of subsequent target detection methods. Thus, state-of-the-art matrix completion methods are applied to the GPR image with missing information in both pixel- and column-wise cases with different missing rates, such as 30% and 50%. After the GPR image is successfully recovered, the faster region-based convolutional neural network (Faster R-CNN) target detection method is applied. The performance correlation between matrix completion accuracy and the target detection method’s confidence score is analyzed using both quantitative and visual results. The obtained results demonstrate the importance of GPR image recovery prior to any post-processing implementation, such as target detection.

Stray Light Nonuniform Background Elimination Method Based on Image Block Self-Adaptive Gray-Scale Morphology for Wide-Field Surveillance

Space-based wide-field surveillance systems are of great significance in maintaining the security of space resources by avoiding collisions between space targets. However, their performance is hindered by stray light phenomena. The nonuniform background noise caused by stray light significantly hampers subsequent target detection, leading to a high frequency of false alarms. To solve this problem, we propose a robust and accurate nonuniform background elimination method based on image block self-adaptive gray-scale morphology (IBSGM). First, we define two kinds of structural operators with different sizes and domains, which make full use of the difference between the target pixels and surrounding background pixels. Then, we block the original surveillance image and find the size of the largest target in each block by the minimum bounding rectangle method to determine the optimal size of the structural operator suitable for each block. Finally, we perform morphological processing using the defined structural operators to eliminate nonuniform backgrounds from images. Experimental results on simulated and real image datasets demonstrate that the proposed IBSGM method has higher precision in eliminating the nonuniform background when compared to other methods.

Super-Pixel Guided Low-Light Images Enhancement with Features Restoration.

Dealing with low-light images is a challenging problem in the image processing field. A mature low-light enhancement technology will not only be conductive to human visual perception but also lay a solid foundation for the subsequent high-level tasks, such as target detection and image classification. In order to balance the visual effect of the image and the contribution of the subsequent task, this paper proposes utilizing shallow Convolutional Neural Networks (CNNs) as the priori image processing to restore the necessary image feature information, which is followed by super-pixel image segmentation to obtain image regions with similar colors and brightness and, finally, the Attentive Neural Processes (ANPs) network to find its local enhancement function on each super-pixel to further restore features and details. Through extensive experiments on the synthesized low-light image and the real low-light image, the experimental results of our algorithm reach 23.402, 0.920, and 2.2490 for Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), and Natural Image Quality Evaluator (NIQE), respectively. As demonstrated by the experiments on image Scale-Invariant Feature Transform (SIFT) feature detection and subsequent target detection, the results of our approach achieve excellent results in visual effect and image features.

Investigation of contact dynamics and cell rheology during early phagocytic binding

Phagocytosis, the process in which phagocytes clear pathogens and apoptotic cells is an important part of our innate immune defense. After cell-target binding and subsequent target detection by receptors in the membrane, the formation of the phagocytic cup around the target is driven by the polymerization of cortical actin. While the main proteins involved in phagosome formation have already been identified, a full model of the uptake process has not been developed yet, in part because mechanical aspects such as the early binding kinetics and the cortical rheology during the process remain largely elusive.

The Multi-domain Union Clutter Suppression Algorithm Based on Robust Principal Component Analysis

In through-the-wall imaging, the clutter cannot be eliminated completely through traditional algorithms, and seriously affects the subsequent target detection and recognition. To solve the problem, based on robust principal component analysis theory, a joint low-rank and sparse model is established in echo and image domain respectively. The models are solved by smoothing fast alternating linearization method. Then, the target images are dealt with exponentially weighted multiply multi-domain image fusion to obtain the final image. The simulation results indicate that the algorithm has great speed and accuracy with effective improvement on imaging quality of targets.

Deep Mutual GAN for Life-Detection Radar Super Resolution

To improve the life-detection radar resolution under certain hardware conditions, in this letter, a deep mutual learning generative adversarial network model (Deep Mutual GAN) is proposed. In the proposed model, the generator can improve the angular resolution of the input low-resolution radar image by five times, which is enough to meet our requirements for the resolution of life detection. We innovatively use two generators in GAN with the same network structure and make the two generators learn from each other. In this way, the learning process of a generator is not only achieved by its confrontation with the discriminator but also guided by another generator. As a result, the knowledge of the generator is no longer only obtained through its own learning; each generator learns knowledge from another generator while learning knowledge by itself. The proposed model can effectively make the convergence of GAN more stable and improves the super resolution effect. We also introduce the details of the network structure of generator and discriminator, in which residual learning and a symmetrical network structure are applied. The experimental results show that the proposed method can achieve state-of-the-art imaging effect, which is meaningful for subsequent target detection and recognition.

Improved TQWT for marine moving target detection

Under the conditions of strong sea clutter and complex moving targets, it is extremely difficult to detect moving targets in the maritime surface. This paper proposes a new algorithm named improved tunable Q-factor wavelet transform (TQWT) for moving target detection. Firstly, this paper establishes a moving target model and sparsely compensates the Doppler migration of the moving target in the fractional Fourier transform (FRFT) domain. Then, TQWT is adopted to decompose the signal based on the discrimination between the sea clutter and the target's oscillation characteristics, using the basis pursuit denoising (BPDN) algorithm to get the wavelet coefficients. Furthermore, an energy selection method based on the optimal distribution of sub-bands energy is proposed to sparse the coefficients and reconstruct the target. Finally, experiments on the Council for Scientific and Industrial Research (CSIR) dataset indicate the performance of the proposed method and provide the basis for subsequent target detection.