Target Detection Task Research Articles

BoT2L-Net: Appearance-Based Gaze Estimation Using Bottleneck Transformer Block and Two Identical Losses in Unconstrained Environments

As a nonverbal cue, gaze plays a critical role in communication, expressing emotions and reflecting mental activity. It has widespread applications in various fields. Recently, the appearance-based gaze estimation method, which utilizes CNN (convolutional neural networks), has rapidly improved the accuracy and robustness of gaze estimation algorithms. Due to their insufficient ability to capture global relationships, the present accuracy of gaze estimation methods in unconstrained environments, has the potential for improvement. To address this challenge, the focus of this paper is to enhance the accuracy of gaze estimation, which is typically measured by mean angular error. In light of Transformer’s breakthrough in image classification and target detection tasks, and the need for an efficient network, the Transformer-enhanced-CNN method is a suitable choice. This paper proposed a novel model for 3D gaze estimation in unconstrained environments, based on the Bottleneck Transformer block and multi-loss methods. Our designed network (BoT2L-Net), incorporates self-attention through the BoT block, utilizing two identical loss functions to predict the two gaze angles. Additionally, the back-propagation network was combined with classification and regression losses, to improve the network’s accuracy and robustness. Our model was evaluated on two commonly used gaze datasets: Gaze360 and MPIIGaze, achieving mean angular errors of 11.53° and 9.59° for front 180° and front-facing gaze angles, respectively, on the Gaze360 testing set, and a mean angular error of 3.97° on the MPIIGaze testing set, outperforming the CNN-based gaze estimation method. The BoT2L-Net model proposed in this paper performs well on two publicly available datasets, demonstrating the effectiveness of our approach.

Spatial biases in approximate arithmetic are subject to sequential dependency effects and dissociate from attentional biases

The notion that mental arithmetic is associated with shifts of spatial attention along a spatially organised mental number representation has received empirical support from three lines of research. First, participants tend to overestimate results of addition and underestimate those of subtraction problems in both exact and approximate formats. This has been termed the operational momentum (OM) effect. Second, participants are faster in detecting right-sided targets presented in the course of addition problems and left-sided targets in subtraction problems (attentional bias). Third, participants are biased toward choosing right-sided response alternatives to indicate the results of addition problems and left-sided response alternatives for subtraction problems (Spatial Association Of Responses [SOAR] effect). These effects potentially have their origin in operation-specific shifts of attention along a spatially organised mental number representation: rightward for addition and leftward for subtraction. Using a lateralised target detection task during the calculation phase of non-symbolic additions and subtractions, the current study measured the attentional focus, the OM and SOAR effects. In two experiments, we replicated the OM and SOAR effects but did not observe operation-specific biases in the lateralised target-detection task. We describe two new characteristics of the OM effect: First, a time-resolved, block-wise analysis of both experiments revealed sequential dependency effects in that the OM effect builds up over the course of the experiment, driven by the increasing underestimation of subtraction over time. Second, the OM effect was enhanced after arithmetic operation repetition compared to trials where arithmetic operation switched from one trial to the next. These results call into question the operation-specific attentional biases as the sole generator of the observed effects and point to the involvement of additional, potentially decisional processes that operate across trials.

MIoP-NMS: Perfecting crops target detection and counting in dense occlusion from high-resolution UAV imagery

When performing dense crops target detection and counting tasks in high-resolution images of large scene, several algorithms such as the standard Non-Maximum Suppression (NMS) and its improved CIoU-NMS and soft-NMS are commonly used to improve the de-duplication performance of the prediction frame in objects detection, which has a high mean average precision (mAP) but the error boundaries may be large. In this research, an improved NMS-based max intersection over portion (MIoP-NMS) algorithm is proposed to address this problem and implemented in the YOLOv4 network framework for single-stage target detection. Using banana tree target detection statistics with different sparsity levels as an experimental case, the mAP obtained by applying the method in the paper reaches about 85%, with a mean counting error of about 1.3%. In comparison with several commonly NMS methods, their mAP values are comparable. However, compared to the 10%∼25% mean count error when using these commonly used methods, the mean count error of the method proposed in the paper is reduced by about 8.7%∼23.7%. The method in the paper estimates the number of banana trees in dense occluded banana forests with about 98.7% accuracy, which is simple and effective, and has significant advantages for accurate detection and counting of dense crops targets in high-resolution images in large scenes.

Underwater target detection algorithm based on improved YOLOv4 with SemiDSConv and FIoU loss function

Underwater target detection is an indispensable part of marine environmental engineering and a fast and accurate method of detecting underwater targets is essential. Although many target detection algorithms have achieved great accuracy in daily scenes, there are issues of low-quality images due to the complex underwater environment, which makes applying these deep learning algorithms directly to process underwater target detection tasks difficult. In this paper, we presented an algorithm for underwater target detection based on improved You Only Look Once (YOLO) v4 in response to the underwater environment. First, we developed a new convolution module and network structure. Second, a new intersection over union loss was defined to substitute the original loss function. Finally, we integrated some other useful strategies to achieve more improvement, such as adding one more prediction head to detect targets of varying sizes, integrating the channel attention into the network, utilizing K-means++ to cluster anchor box, and utilizing different activation functions. The experimental results indicate that, in comparison with YOLOv4, our proposed algorithm improved the average accuracy of the underwater dataset detection by 10.9%, achieving 91.1%, with a detection speed of 58.1 frames per second. Therefore, compared to other mainstream target detection algorithms, it is superior and feasible for applications in intricate underwater environments.

Reading fluency and statistical learning across modalities and domains: Online and offline measures.

The vulnerability of statistical learning has been demonstrated in reading difficulties in both the visual and acoustic modalities. We examined segmentation abilities of Hungarian speaking adolescents with different levels of reading fluency in the acoustic verbal and visual nonverbal domains. We applied online target detection tasks, where the extent of learning is reflected in differences between reaction times to predictable versus unpredictable targets. Explicit judgments of well-formedness were also elicited in an offline two-alternative forced choice (2AFC) task. Learning was evident in both the acoustic verbal and visual nonverbal tasks, both in online and offline measures, but learning effects were larger both in online and offline tasks in the verbal acoustic condition. We haven't found evidence for a significant relationship between statistical learning and reading fluency in adolescents in either modality. Together with earlier findings, these results suggest that the relationship between reading and statistical learning is dependent on the domain, modality and nature of the statistical learning task, on the reading task, on the age of participants, and on the specific language. The online target detection task is a promising tool which can be adapted to a wider set of tasks to further explore the contribution of statistical learning to reading acquisition in participants from different populations.

A pupillometric investigation of state regulation in adults scoring high versus low on ADHD symptomatology

According to the state regulation deficit (SRD) account, ADHD is associated with difficulties regulating tonic arousal levels, which may be due to inefficient effort allocation. We aimed to test the SRD account by using a target detection task with three different event rates (ER; 700 ms, 1800 ms, 6000 ms), in order to manipulate the tonic arousal state and its effects on performance and pupil indices in adults with high (n = 40) versus low (n = 36) ADHD symptom levels. In an additional condition, a fast ER (700 ms) was accompanied by auditory white noise (WN), to further increase tonic arousal level. The ER manipulation had a clear effect on RT and variability of RT. These effects were more pronounced for the high-ADHD group, especially for variability of RT with decreasing ER, suggestive of deficient upregulation of a tonic arousal state in that group, in line with their self-reported SRDs in daily life. Adding WN to the fast condition led to more errors, however similarly for both groups. Contrary to our predictions, the ER manipulation had no effect on tonic pupil size (as a measure of tonic arousal). Phasic pupil amplitude (as a measure of cognitive effort) linearly increased with decreasing ER, suggesting more effort allocation during slower ERs. WN decreased phasic pupil amplitude, but had no impact on tonic pupil size. Importantly, however, no ADHD-related differences were present for the pupil indices. In conclusion, adults with elevated levels of ADHD symptoms reported more SRDs in daily life and showed a performance pattern that suggests difficulties in upregulating but not downregulating the tonic arousal state. Surprisingly, these findings were not accompanied by group differences in pupillometric indices. This casts some doubts on the relationship between these measures of autonomic nervous system activity and state regulation, in particular in the context of ADHD symptomatology.

EEG study of attention on an auditory target detection task in dolphins and humans

How do dolphins attend to echos and ignore background noise? Is the process similar to how humans attend to conversations in a crowded room? Studies of human selective attention have highlighted endogenous brain processes modulating the magnitude of early responses to sounds in auditory evoked potentials (AEPs), yet these rely on task-specific instructions difficult to employ in animal studies. We trained an adult male dolphin (Tursiops truncatus) to attend to a stream of rapidly presented tones, and provide a whistle response to a “target” tone while withholding responses to “background” tones in an amplitude discrimination task. The background sounds were designed to function as a tonal mismatch negativity paradigm with two frequencies: a standard tone presented 80% of the time, and a deviant presented 20% of the time. Depending on condition, the target could be the same frequency as the standard or the deviant. We observed an enhanced AEP response to a deviant of the same frequency as the target, while the AEP response to the standard-target condition was reduced. This was not predicted by previous human experiments, and we are currently following up with a pilot a human task modeled after the dolphin implicit target detection task.

Enhanced target detection using a new cognitive sonar waveform design in shallow water

A cognitive waveform design is proposed for use in SONARs (Sound Operated Navigation and Ranging) for detecting targets in undersurface environment. The study adopts a waveform design procedure exploiting prior knowledge gained from environmental reverberations and target signals based on maximizing signal- to- interference-plus- noise ratio (SINR) in the receiver. A genetic algorithm is set forth to work out the optimal specifications in a wideband waveform design. Using initial Linear Frequency Modulated (LFM) waveform as input to the proposed optimization algorithm, an optimal waveform is obtained showing significant improvements in SINR. A number of experiments are conducted to simulate Probability of Detection (POD) versus Signal-to-Reverberation Ratio (SRR) in underwater environments. Analyzing simulation results reveals considerable improvements in target detection task utilizing optimal waveform design compared to initial LFM waveform. Also, in comparison with the initial LFM waveform, it was noticed that there was a substantial reduction in the bandwidth of the optimized design waveform.Our proposed method solves the problem of finding the optimal frequency for designing a cognitive waveform appropriate to the conditions of the environment and the target. We proposed the genetic algorithm method to solve the waveform design problem that maximize the SINR. This paper provides a general methodology for extracting the optimal frequency parameters of the waveform and can be extended to other parameters in cognitive design.

Lightweight algorithm for multi-scale ship detection based on high-resolution SAR images

ABSTRACT As ship target detection technology has high application value in military and civil fields, it is significant to research ship detection in SAR images. Aiming at the complex and diverse backgrounds, significant differences in ship sizes, and real-time detection problems in the ship target detection task of SAR remote sensing images, a lightweight ship detection network based on the YOLOx-Tiny model is proposed. Firstly, a multi-scale ship feature extraction module is proposed, composed of a parallel multi-branch structure connected by a standard convolution layer, asymmetric convolution layer, and dilatation convolution layer with different expansion rates in turn. It makes better use of local features and global features and effectively improves the detection accuracy of multi-scale ship targets; Secondly, to ensure detection performance and eliminate background interference, we propose a whole SAR remote sensing image detection strategy based on an adaptive threshold, which effectively suppresses false alarms caused by background and improves detection speed. The experimental results on two different SAR ship datasets, SSDD and HRSID, show that, compared with several advanced methods, the effectiveness and superiority of the method in this paper are verified, and excellent results are shown in the detection of the whole SAR remote-sensing image. It can provide effective theoretical and technical support for ship detection on platforms with limited computing resources and has good application prospects.

FESSD: Feature Enhancement Single Shot MultiBox Detector Algorithm for Remote Sensing Image Target Detection

Automatic target detection of remote sensing images (RSI) plays an important role in military surveillance and disaster monitoring. The core task of RSI target detection is to judge the target categories and precise location. However, the existing target detection algorithms have limited accuracy and weak generalization capability for RSI with complex backgrounds. This study presents a novel feature enhancement single shot multibox detector (FESSD) algorithm for remote sensing target detection to achieve accurate detection of different categories targets. The FESSD introduces feature enhancement module and attention mechanism into the convolution neural networks (CNN) model, which can effectively enhance the feature extraction ability and nonlinear relationship between different convolution features. Specifically, the feature enhancement module is used to extract the multi-scale feature information and enhance the model nonlinear learning ability; the self-learning attention mechanism (SAM) is used to expand the convolution kernel local receptive field, which makes the model extract more valuable features. In addition, the nonlinear relationship between different convolution features is enhanced using the feature pyramid attention mechanism (PAM). The experimental results show that the mAP value of the proposed method reaches 81.9% and 81.2% on SD-RSI and DIOR datasets, which is superior to other compared state-of-the-art methods.

Underwater Target Detection Algorithm Based on Improved YOLOv5

In order to solve the problem of low accuracy of traditional methods in underwater target detection and recognition, an underwater target detection algorithm based on YOLOv5, adding Convolutional Block Attention Module (CBAM) and Bidirectional Feature Pyramid Network (BIFPN) is proposed in this paper. In this method, CBAM is introduced into the output of YOLOv5 network model, and the attention module is used to fuse and enhance the features in channel dimension and spatial dimension, so as to enhance the features of target area features and improve the detection accuracy of small targets. At the same time, the simplified BIFPN module is used to replace the original enhanced feature extraction network in the Neck to improve the feature extraction ability of the network for different scales. The experimental results show that the mAP_0.5 is 84.2%, which is 0.9% higher than YOLOv5s model, meeting the needs of underwater target detection tasks.

Visualization and Object Detection Based on Event Information.

A dynamic vision sensor is an optical sensor that focuses on dynamic changes and outputs event information containing only position, time, and polarity. It has the advantages of high temporal resolution, high dynamic range, low data volume, and low power consumption. However, a single event can only indicate that the increase or decrease in light exceeds the threshold at a certain pixel position and a certain moment. In order to further study the ability and characteristics of event information to represent targets, this paper proposes an event information visualization method with adaptive temporal resolution. Compared with methods with constant time intervals and a constant number of events, it can better convert event information into pseudo-frame images. Additionally, in order to explore whether the pseudo-frame image can efficiently complete the task of target detection according to its characteristics, this paper designs a target detection network named YOLOE. Compared with other algorithms, it has a more balanced detection effect. By constructing a dataset and conducting experimental verification, the detection accuracy of the image obtained by the event information visualization method with adaptive temporal resolution was 5.11% and 4.74% higher than that obtained using methods with a constant time interval and number of events, respectively. The average detection accuracy of pseudo-frame images in the YOLOE network designed in this paper is 85.11%, and the number of detection frames per second is 109. Therefore, the effectiveness of the proposed visualization method and the good performance of the designed detection network are verified.

Underwater Reverberation Suppression via Attention and Cepstrum Analysis-Guided Network

Active sonar systems are one of the most commonly used acoustic devices for underwater equipment. They use observed signals, which mainly include target echo signals and reverberation, to detect, track, and locate underwater targets. Reverberation is the primary background interference for active sonar systems, especially in shallow sea environments. It is coupled with the target echo signal in both the time and frequency domain, which significantly complicates the extraction and analysis of the target echo signal. To combat the effect of reverberation, an attention and cepstrum analysis-guided network (ACANet) is proposed. The baseline system of the ACANet consists of a one-dimensional (1D) convolutional module and a reconstruction module. These are used to perform nonlinear mapping and to reconstruct clean spectrograms, respectively. Then, since most underwater targets contain multiple highlights, a cepstrum analysis module and a multi-head self-attention module are deployed before the baseline system to improve the reverberation suppression performance for multi-highlight targets. The systematic evaluation demonstrates that the proposed algorithm effectively suppresses the reverberation in observed signals and greatly preserves the highlight structure. Compared with NMF methods, the proposed ACANet no longer requires the target echo signal to be low-rank. Thus, it can better suppress the reverberation in multi-highlight observed signals. Furthermore, it demonstrates superior performance over NMF methods in the task of reverberation suppression for single-highlight observed signals. It creates favorable conditions for underwater platforms, such as unmanned underwater vehicles (UUVs), to carry out underwater target detection and tracking tasks.

A double-layer feature fusion convolutional neural network for infrared small target detection

ABSTRACT Infrared small target detection is critical in remote sensing, military, and other fields. However, the low resolution of most infrared images and the lack of texture and detailed information could cause the target to be lost in a relatively noisy background. Therefore, in recent years, researchers have paid particular attention to the problem of small infrared target detection. In this paper, we propose a double-layer feature fusion convolutional neural network for infrared small target detection (DLFF), consisting of a simultaneous upsampling two-layer network module and a ‘T’-type fusion structure. First, the upsampling double-layer network module shares detection information while synchronizing detection, suppressing the background noise and enhancing the detection of the target. In addition, for the small target detection task, since the direct fusion of shallow spatial information and deep semantic information may lose only some small target features, we propose a ‘T’-type fusion structure to solve this problem. Furthermore, we collate an infrared small target dataset (MDFA_SIRIST) and design a pre-processing method for pre-detection images. The experimental results show that our network outperforms the other six state-of-the-art methods in combined evaluation metrics ( -score) and mean intersection ratio (mIou).

Cross-modal guiding and reweighting network for multi-modal RSVP-based target detection

Rapid Serial Visual Presentation (RSVP) based Brain–Computer Interface (BCI) facilities the high-throughput detection of rare target images by detecting evoked event-related potentials (ERPs). At present, the decoding accuracy of the RSVP-based BCI system limits its practical applications. This study introduces eye movements (gaze and pupil information), referred to as EYE modality, as another useful source of information to combine with EEG-based BCI and forms a novel target detection system to detect target images in RSVP tasks. We performed an RSVP experiment, recorded the EEG signals and eye movements simultaneously during a target detection task, and constructed a multi-modal dataset including 20 subjects. Also, we proposed a cross-modal guiding and fusion network to fully utilize EEG and EYE modalities and fuse them for better RSVP decoding performance. In this network, a two-branch backbone was built to extract features from these two modalities. A Cross-Modal Feature Guiding (CMFG) module was proposed to guide EYE modality features to complement the EEG modality for better feature extraction. A Multi-scale Multi-modal Reweighting (MMR) module was proposed to enhance the multi-modal features by exploring intra- and inter-modal interactions. And, a Dual Activation Fusion (DAF) was proposed to modulate the enhanced multi-modal features for effective fusion. Our proposed network achieved a balanced accuracy of 88.00% (±2.29) on the collected dataset. The ablation studies and visualizations revealed the effectiveness of the proposed modules. This work implies the effectiveness of introducing the EYE modality in RSVP tasks. And, our proposed network is a promising method for RSVP decoding and further improves the performance of RSVP-based target detection systems.

Surface defect detection method for electronic panels based on attention mechanism and dual detection heads.

Automatic detection of surface defects in electronic panels is receiving increasing attention in the quality control of products. The surface defect detection of electronic panels is different from other target detection scenarios and is a meaningful and challenging problem. Its main manifestation is that surface defects of electronic panels usually exhibit extreme irregularity and small target characteristics, which bring great difficulties to the task of surface defect target detection including feature extraction and so on. The traditional methods can only detect a very small number of defect classes under specific detection conditions. And due to the weak robustness of these methods, they cannot be applied in real production scenarios on a large scale. Based on this, this paper applies the target detection technique under deep learning to the surface defect detection scenario of electronic panels for the first time. At the same time, in order to make the designed target detection network applicable to the electronic panel surface defect detection scenario and to enhance the interpretability of the designed target detection network in terms of computer mechanism. We design a deformable convolution module with a convolutional self-attentive module to learn the offset and a dual detection head incorporating the SE (Squeeze-and-Excitation) mechanism for the irregular characteristics of electronic panel surface defects and the small target characteristics, respectively. Finally, we carried out a series of experiments on our own electronic panel defect data set, including comparison with the most advanced target detection algorithms and a series of ablation experiments against our proposed method. The final experimental results prove that our method not only has better interpretability, but also has better metric performance, in which the map_0.5 metric reaches 78.257%, which is an increase of 13.506 percentage points over YOLOV5 and 33.457 percentage points higher than Retinanet. The results prove the proposed method is effective.

Responsiveness variability during anaesthesia relates to inherent differences in brain structure and function of the frontoparietal networks.

Anaesthesia combined with functional neuroimaging provides a powerful approach for understanding the brain mechanisms of consciousness. Although propofol is used ubiquitously in clinical interventions that reversibly suppress consciousness, it shows large inter-individual variability, and the brain bases of this variability remain poorly understood. We asked whether three networks key to conscious cognition-the dorsal attention (DAN), executive control (ECN), and default mode (DMN)-underlie responsiveness variability under anaesthesia. Healthy participants (N= 17) were moderately anaesthetized during narrative understanding and resting-state conditions inside the Magnetic Resonance Imaging scanner. A target detection task measured behavioural responsiveness. An independent behavioural study (N= 25) qualified the attention demands of narrative understanding. Then, 30% of participants were unaffected in their response times, thus thwarting a key aim of anaesthesia-the suppression of behavioural responsiveness. Individuals with stronger functional connectivity within the DAN and ECN, between them, and to the DMN, and with larger grey matter volume in frontal regions were more resilient to anaesthesia. For the first time, we show that responsiveness variability during propofol anaesthesia relates to inherent differences in brain structure and function of the frontoparietal networks, which can be predicted prior to sedation. Results highlight novel markers for improving awareness monitoring during clinical anaesthesia.

Blind Super-Resolution for SAR Images with Speckle Noise Based on Deep Learning Probabilistic Degradation Model and SAR Priors

As an active microwave coherent imaging technology, synthetic aperture radar (SAR) images suffer from severe speckle noise and low-resolution problems due to the limitations of the imaging system, which cause difficulties in image interpretation and target detection. However, the existing SAR super-resolution (SR) methods usually reconstruct the images by a determined degradation model and hardly consider multiplicative speckle noise, meanwhile, most SR models are trained with synthetic datasets in which the low-resolution (LR) images are down-sampled from their high-resolution (HR) counterparts. These constraints cause a serious domain gap between the synthetic and real SAR images. To solve the above problems, this paper proposes an unsupervised blind SR method for SAR images by introducing SAR priors in a cycle-GAN framework. First, a learnable probabilistic degradation model combined with SAR noise priors was presented to satisfy various SAR images produced from different platforms. Then, a degradation model and a SR model in a unified cycle-GAN framework were trained simultaneously to learn the intrinsic relationship between HR–LR domains. The model was trained with real LR and HR SAR images instead of synthetic paired images to conquer the domain gap. Finally, experimental results on both synthetic and real SAR images demonstrated the high performance of the proposed method in terms of image quality and visual perception. Additionally, we found the proposed SR method demonstrates the tremendous potential for target detection tasks by reducing missed detection and false alarms significantly.

L₁ Sparsity-Regularized Attention Multiple-Instance Network for Hyperspectral Target Detection.

Attention-based deep multiple-instance learning (MIL) has been applied to many machine-learning tasks with imprecise training labels. It is also appealing in hyperspectral target detection, which only requires the label of an area containing some targets, relaxing the effort of labeling the individual pixel in the scene. This article proposes an L1 sparsity-regularized attention multiple-instance neural network (L1-attention MINN) for hyperspectral target detection with imprecise labels that enforces the discrimination of false-positive instances from positively labeled bags. The sparsity constraint applied to the attention estimated for the positive training bags strictly complies with the definition of MIL and maintains better discriminative ability. The proposed algorithm has been evaluated on both simulated and real-field hyperspectral (subpixel) target detection tasks, where advanced performance has been achieved over the state-of-the-art comparisons, showing the effectiveness of the proposed method for target detection from imprecisely labeled hyperspectral data.

Tensor Spectral k-Support Norm Minimization for Detecting Infrared Dim and Small Target Against Urban Backgrounds

In the low-altitude urban background with heavy interference, especially in the face of corner interference with higher intensity than the target, infrared (IR) dim and small target is extremely lack of prior information (i.e., size, shape and contrast information). In such case, the existing detection methods usually suffer from high false alarm or even failure. To deal with this situation, we develop a novel spatial-temporal tensor model with tensor spectral <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> -support norm minimization (STTM-TSNM) for detecting IR dim and small target. Firstly, the spatial-temporal information of the original image sequence can be preserved completely by constructing the holistic STTM. Then, according to the spatial-temporal related prior knowledge of the target and background, the target detection task is customized as an optimization problem of low rank and sparse tensor recovery. To better preserve the internal structure and capture more global information, the tensor spectral <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> -support norm minimization is introduced as the regularization term of the constraint background. Finally, draw support from the framework of alternating direction method of multipliers (ADMM) algorithm, the precise separation of target and background is achieved. In addition, to promote the prosperity of sequential detection methods, we released to the scientific community a small IR target dataset containing six image sequences with urban background. The experimental results on six real IR sequences demonstrate that our method outputs the most outstanding detection performance compared with the latest sequential detection methods.