Global Spatial Information Research Articles

Capturing Small, Fast-Moving Objects: Frame Interpolation via Recurrent Motion Enhancement

Interpolating video frames involving large motions remains an elusive challenge. In case that frames involve small and fast-moving objects, conventional feed-forward neural network-based approaches that estimate optical flow and synthesize in-between frames sequentially often result in loss of motion features and thus blurred boundaries. To address the problem, we propose a novel Recurrent Motion-Enhanced Interpolation Network (ReMEI-Net) by assigning attention to the motion features of small objects from both the intra-scale and inter-scale perspectives. Specifically, we add recurrent feedback blocks in the existing multi-scale autoencoder pipeline, aiming to iteratively enhance the motion information of small objects across different scales. Second, to further refine the motion features of the highly moving objects, we propose a Multi-Directional ConvLSTM (MD-ConvLSTM) block to capture the global spatial contextual information of motion from multiple directions. In this way, the coarse-scale features can be utilized to correct and enhance the fine-scale features through the feedback mechanism. Extensive experiments on various datasets demonstrate the superiority of our proposed method over state-of-the-art approaches in terms of clear locations and complete shape.

Accuracy Assessment of Kriging, artificial neural network, and a hybrid approach integrating spatial and terrain data in estimating and mapping of soil organic carbon.

This study aimed to produce a soil organic carbon (SOC) content map with high accuracy and spatial resolution using the most effective factors in the model. The spatial SOC estimation success of Inverse Distance Weighting (IDW), Ordinary Kriging (OK), Empirical Bayesian Kriging (EBK), Multi-Layered Perception Network (MLP) and MLP-OK Hybrid models were compared to obtain the most reliable model in estimating the SOC content. The study area was located in Besni district in the Southeastern Anatolia Region of Turkey. Total of 132 surface (0–30 cm) soil samples were collected from the covers 1330 km2 land and analyzed for SOC, lime, clay and sand content and soil reaction included in the estimation models. Mean annual precipitation and temperature, elevation, compound topographic index, enhanced vegetation and normalized difference vegetation index, were also used as the inputs in the modelling. The spatial distribution of SOC was determined using a MLP and a two-stage ensemble model (MLP-OK) combining the estimation of OK residuals. Soil surveys and covariates were used to train and validate the MLP-OK hybrid model. The MLP-OK model provided a more accurate estimation of SOC content with minimal estimation errors (ME: -0.028, 45 MAE: 0.042, RMSE: 0.066) for validation points compared to the other models. The MLP-OK model outperformed other models by 75.09 to 77.92%. The MLP-OK model estimated the lower and upper limits of the estimated and the measured values in a consistent manner compared to the other models. The spatial distribution map of SOC content obtained by ANN-kriging approach was significantly affected by ancillary variables, and revealed more detail than other interpolation methods in the northern, central, southwestern and southeastern parts of the study area. The results revealed that the assembling of MLP with OK model can contribute to obtain more reliable regional, national and global spatial soil information.

Underwater image super-resolution and enhancement via progressive frequency-interleaved network

Underwater images usually contain severely blurred details, color distortion, and low contrast, warranting efficient methods to obtain clean images. However, most convolutional neural network-based approaches involve high computational cost, numerous model parameters, and even poor performance. Besides, the mapping from input to output is learned using a single path, ignoring the frequency domain information. To solve these challenges, we propose a novel progressive frequency-interleaved network (PFIN) for underwater imagery super-resolution and enhancement. Specifically, progressive frequency-domain module (PFDM) and convolution-guided module (CGM) constitute PFIN for effective color deviation correction and detail enhancement. PFDM that possesses global spatial attention, multi-scale residual, and frequency information modulation blocks gradually learn frequency features and explicitly compensate for detail loss. Furthermore, CGM comprising a series of convolution blocks generates discriminative characteristics to modulate in PFDM for better accommodating degraded representations. Extensive experiments demonstrate the superiority of our PFIN regarding quantitative evaluations and visual quality.

Full transformer network with masking future for word-level sign language recognition

Word-level sign language recognition (SLR) is a significant task which transcribes a sign language video into a word. Currently, deep-learning-based frameworks mostly combine spatial feature extractors based on convolution neural networks (CNNs) and sequence learners. These methods either lack the sufficient capacity to establish the high-level vision semantic knowledge and incorporate the details in images or perform weak intelligence on video frame sequence comprehension. Focusing on gestures and facial expressions is essential to interpreting sign language; however, it is challenging to crop these elements from pictures and distill them end-to-end. In this paper, a full self-attention framework for word-level SLR is proposed to tackle the above issue, which integrates a Vision Transformer as spatial encoder and an improved temporal Transformer. In addition, we introduce the masking future operation to improve the Transformer for the temporal module. The vision Transformer first refines the latent high-level semantic feature sequences from sign language videos and feeds them into the temporal module. Then the masking future Transformer enhances this sequence by making subsequent time invisible at each moment of frames and generates the final recognition. This approach integrates global and local spatial information; furthermore, it can also distinguish the latent semantic features contained in sign language action sequences. To validate the proposed approach, we perform extensive experiments on two datasets. The results and ablation studies demonstrate the effectiveness of this method, and it achieves new state-of-the-art performance on the WLASL dataset by using RGB images alone.

Few-Shot Learning with Collateral Location Coding and Single-Key Global Spatial Attention for Medical Image Classification

Humans are born with the ability to learn quickly by discerning objects from a few samples, to acquire new skills in a short period of time, and to make decisions based on limited prior experience and knowledge. The existing deep learning models for medical image classification often rely on a large number of labeled training samples, whereas the fast learning ability of deep neural networks has failed to develop. In addition, it requires a large amount of time and computing resource to retrain the model when the deep model encounters classes it has never seen before. However, for healthcare applications, enabling a model to generalize new clinical scenarios is of great importance. The existing image classification methods cannot explicitly use the location information of the pixel, making them insensitive to cues related only to the location. Besides, they also rely on local convolution and cannot properly utilize global information, which is essential for image classification. To alleviate these problems, we propose a collateral location coding to help the network explicitly exploit the location information of each pixel to make it easier for the network to recognize cues related to location only, and a single-key global spatial attention is designed to make the pixels at each location perceive the global spatial information in a low-cost way. Experimental results on three medical image benchmark datasets demonstrate that our proposed algorithm outperforms the state-of-the-art approaches in both effectiveness and generalization ability.

GssMILP for anomaly classification in surveillance videos

Multiple Instance Learning (MIL) is widely used to locate abnormal video frames in surveillance videos due to its ability to work with weakly-labeled data. On the other hand, graph-based semi-supervised approaches are employed to handle label sparsity-related issues such as Low Degree-of-Supervision (LDoS) and High Class-Imbalance (HCI). However, the application of the MIL paradigm in anomaly classification of surveillance videos faces significant challenges such as (i) LDoS, (ii) HCI, and (iii) A multitude of types of abnormal events and actions instead of a unique pattern. The current work proposes a novel anomaly classifier to address these issues with a new objective function (GssMILP) by leveraging the benefits from graph-based semi-supervised and multiple-instance learning approaches. In this regard, our contributions are six-fold. First, a deep hierarchical architecture (C3D+3DCNN BICLSTM) to extract generic video descriptors. These descriptors represent the multitude of types of abnormal events and actions by incorporating the local–global spatial information and long-short-term temporal information related to the object motion, human actions, and behavioral features. Second, we develop a learning objective (GssMILP) that extends the MIL-based instance-level labeler to graph-based semi-supervising. Third, we use three different regularizer terms, namely graph-based regularizer, non-convex L2-regularizer, and temporal-smoothness regularizer. Fourth, we present an elaborate experimental study comparing the performance of the proposed approach with six similar baseline approaches. The results indicate that at degree-of-supervision 1.0%, the proposed method improves the f1-score by 45.26%, 18.19%, 45.28%, and 9.22% in UCSD-ped1, UCSD-ped2, MED, and RWAD datasets, respectively. Fifth, we present an ablation study on the impact of different features on the performance of an anomaly classifier. Sixth, we provide temporal annotations for a label resource of 1900 videos in the RWAD dataset.

Spatio-Temporal Coding-Based Helicopter Trajectory Planning for Pulsed Neural Membrane System.

For the trajectory planning problem under the nonlinear and strongly coupled characteristics of unmanned helicopters, membrane computing with distributed parallel processing capability is introduced for unmanned helicopter trajectory planning. The global and local spatial information is temporally characterized; the temporal characterization algorithm under mapping information is designed; the hierarchical discriminant regression algorithm is designed based on incremental principal component analysis to realize the process of building and identifying trees in trajectory planning; and the pulsed neural membrane system (PNMS) with spatio-temporal coding function under membrane computing is constructed. Compared with the RRT algorithm in two experimental environments, the original path length, the trimmed path length, the time used to plan the trajectory, and the number of search nodes have different levels of improvement; the feasibility and effectiveness of the PNMS in unmanned helicopter trajectory planning are verified. It expands the theoretical research of membrane computing in the field of optimal control and provides theoretical support for the subsequent application practice.

A Global Spectral–Spatial Feature Learning Network for Semisupervised Hyperspectral Unmixing

Neural networks have been widely applied in hyperspectral unmixing in the past few years. However, most networks only focus on extracting the spectral information or local spectral–spatial correlation of a single pixel. In order to further explore the spectral–spatial information of hyperspectral images (HSIs) and improve the effective use of spatial information in unmixing tasks, an end-to-end semisupervised unmixing network is proposed in this article. At the encoder, the dual branch network performs convolution operations along the spatial dimension and the spectral dimension, respectively, to realize the separated extraction of global spatial and spectral information; the spectral–spatial attention residual module then fuses the separated spectral–spatial features into the joint spectral–spatial information. The encoder is to realize mapping from high-dimensional spectral data to latent abundance representations. The decoder is a simple linear fully connected layer whose weight is fixed to a known spectral library to complete the reconstruction of the HSI. Experiments on two synthetic datasets and two real datasets demonstrate the superior performance of the proposed method, and prove the effectiveness of considering global spatial information in the unmixing task.

Grouped Bidirectional LSTM Network and Multistage Fusion Convolutional Transformer for Hyperspectral Image Classification

The efficiently and effectively discriminative spectral-spatial feature representation is essential for hyperspectral image (HSI) classification. However, most of the existing methods rely on the patch-based convolutional neural networks (CNNs) whose ability of extracting the global spatial information is very limited. To address this issue, in this paper, we propose a two-branch network consisting of a grouped bidirectional long short-term memory (GBiLSTM) network and multi-stage fusion convolutional transformer (MFCT) for HSI classification. In the proposed GBiLSTM-MFCT, to extract the spectral features of HSI efficiently, a GBiLSTM network is designed by dividing the sequence features and hidden units of BiLSTM network into several separate groups. To simultaneously extract the global and local spatial features of HSI, a MFCT is proposed by fusing the features of different levels obtained from the multiple phases of convolutional vision transformer. Moreover, in the multi-headed attention module of each stage, blueprint separable convolution based self-attention (BSCA) module is designed which is able to model the global and local spatial information effectively. The outputs of GBiLSTM network and MFCT are fused to generate discriminative and robust spectral-spatial features for HSI classification. Experiments on three benchmark data sets of IN, UP and KSC demonstrate that the proposed GBiLSTM-MFCT exhibits higher classification performance with very limited labeled samples than eight state-of-the-art methods.

Global to Local: A Hierarchical Detection Algorithm for Hyperspectral Image Target Detection

Hyperspectral image (HSI) has received considerable attention in the field of target detection due to its powerful ability to capture the spectral information of land covers, and plenty of detection algorithms have been explored. However, these methods generally leverage the difference between the spectrum of the target to be detected and the background spectrum to accomplish target detection, and so are susceptible to the problem of spectral variability. In this article, we propose a global-to-local hierarchical detection algorithm for HSI (G2LHTD). Firstly, extended morphological attribute profile (EMAP) is first used to model global spatial texture information from HSI. Subsequently, a diverse-direction constrained energy minimization (D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> CEM) detector is developed to consider the spatial information within eight neighborhoods around each pixel in HSI, yielding comprehensive local spatial information. More substantially, to effectively discriminate the neighborhood information in diverse directions, we devise an adaptive neighborhood feature aggregation (ANFA) strategy, which will comprehensively evaluate the significance of neighborhood information in diverse directions. As a result, the spatial features of HSI can be comprehensively considered for hyperspectral target detection (HTD). Extensive experiments, conducted on four standard datasets, demonstrate the effectiveness of the proposed method. The codes of this work will be available at https://github.com/zhonghaocheng/G2LHTD_Master for the sake of reproducibility.

Adaptive Spatial Pyramid Constraint for Hyperspectral Image Classification With Limited Training Samples

Deep learning-based methods have made significant progress in hyperspectral image (HSI) classification in recent years. However, deep learning-based methods usually rely on a large number of samples, and in many cases, it is difficult to label HSI and only limited training samples are available. To solve this problem, an HSI classification method based on adaptive spatial pyramid constraint (ASPC) is proposed to make full use of the global spatial neighborhood information of the labeled samples, which can improve the generalization ability of the classification model. The main steps of the proposed method are as follows. First, an HSI complexity evaluation method based on edge detection is proposed to assess the homogeneity of the objects in the HSI. Second, an HSI pyramid segmentation method based on spatial pyramid is proposed to generate multiscale subregions, where HSI complexity is used to adaptively determine the scale of the segmentation. Third, a spatial supervised constraint is proposed to generate the loss function of labeled subregions. Fourth, a spatial unsupervised constraint is proposed to generate the loss function of unlabeled subregions. The proposed method fully explores the spatial-spectral correlation between unlabeled samples and labeled samples, and add corresponding constraints to the training objective according to the correlation. By adding the ASPC, the trained model becomes more robust and can make full use of the limited training samples. To verify the effectiveness of the proposed method, three benchmark hyperspectral datasets are used to verify the performance of the proposed method. Experimental results show that the performance of this method is better than the existing state-of-the-art methods.

SFR-Net: Scattering Feature Relation Network for Aircraft Detection in Complex SAR Images

Aircraft detection in synthetic aperture radar (SAR) images plays a significant role in dynamic monitoring and national security. Previous methods have difficulty in obtaining the desirable detection performance due to the interference of complex scenes and diversity of aircraft sizes. In order to solve these problems, we propose an innovative scattering feature relation network (SFR-Net) in this article. First, considering that the strong scattering points of the aircraft in SAR images are usually discrete, we leverage the proposed scattering point relation module to fulfill the analysis and correlation of scattering points. By enhancing the characteristics and relationships among the scattering points, this method is beneficial to guarantee the completeness of aircraft detection results. Second, we design a salient fusion module to adaptively aggregate the features from different layers of SFR-Net with rich semantic information and plentiful details, which can highlight the significant objects with different sizes and enhance the distinguishable features. Third, to reduce the false alarm and improve the localization accuracy, the contextual feature attention is presented to capture the global spatial and semantic information with a large receptive field. Overall, the SFR-Net is designed based on the SAR imaging mechanism and the scattering characteristics of aircrafts. The extensive experiments are conducted on the SAR aircraft detection dataset (AIRD) from the Gaofen-3 satellite to demonstrate the effectiveness of the SFR-Net and also illustrate that our method achieves state-of-the-art performance.

Hyperspectral Image Classification Based on Multibranch Attention Transformer Networks

Deep learning has become a mainstream method of hyperspectral image (HSI) classification. Many DL-based methods exploit spatial-spectral features to achieve better classification results. However, due to the complex backgrounds in HSIs, existing methods usually show unsatisfactory performance for the class pixels located on the land-cover category boundary area. In large part, this is because the network is susceptible to interference by the irrelevant information around the target pixel in the training stage, resulting in inaccurate feature extraction. In this paper, a new multibranch transformer architecture (SST-M) that assembles spatial attention and extracts spectral features is proposed to address this problem. The transformer model has a global receptive field and thus can integrate global spatial position information in the HSI cube. Meanwhile, we design a spatial sequence attention model to enhance the useful spatial location features and weaken invalid information. Considering that HSIs contain considerable spectral information, a spectral feature extraction model is designed to extract discriminative spectral features, replacing the widely used PCA method and obtaining better classification results than it. Finally, inspired by semantic segmentation, a mask prediction model is designed to classify all of the pixels in the HSI cube; this guides the neural network to learn precise pixel characteristics and spatial distributions. To verify the effectiveness of our algorithm (SST-M), quantitative experiments were conducted in three well-known datasets, namely, IP, PU, and KSC. The experimental results demonstrate that the proposed model achieves better performance than the other state-of-the-art methods.

SPNet: Spectral Patching End-to-End Classification Network for UAV-Borne Hyperspectral Imagery With High Spatial and Spectral Resolutions

In deep learning (DL)-based hyperspectral imagery classification, &#x201C;spatial patching&#x201D; is primarily used as a preprocessing for incorporating local spatial information. This operation can help to promote classification accuracy but it is facing new challenges in the unmanned aerial vehicle (UAV)-borne hyperspectral imagery with high spatial and spectral resolutions (H² imagery). The ground objects&#x2019; various spatial scales result in it being challenging to determine the optimal size for the spatial patches. In addition, due to the severe spectral variability and spatial heterogeneity of the H² imagery, &#x201C;spatial patching&#x201D; only exploits the local spatial information and results in serious salt-and-pepper (SP) noise and isolated areas in the classification maps. In this article, to address these issues, a novel spectral patching network (SPNet) with an end-to-end DL architecture is proposed for UAV-borne H² imagery classification. The &#x201C;spectral patching&#x201D; approach is proposed to preserve the global spatial information and almost all the spectral information of the original hyperspectral imagery. An end-to-end deep encoder&#x2013;decoder network is then constructed based on the spectral patching mechanism, which introduces the deep residual network (ResNet) and atrous spatial pyramid pooling (ASPP) modules to extract multiscale high-level semantic information for the H² imagery classification. The experimental results obtained with the Wuhan UAV-borne H² imagery (WHU-Hi) UAV-borne hyperspectral data set demonstrate that SPNet can achieve state-of-the-art accuracy and visualization performance in the classification of H² imagery.

Research on the Geometric Precision Correction Method for Three-Axis-Stabilized Geostationary Meteorological Satellite Images Based on Landmarks

To improve the positioning accuracy of the three-axis-stabilized geostationary meteorological satellite (GSMS) images, we developed a geometric precision correction process based on landmarks. For the problem that GSMS images and binary landmark images are difficult to match accurately, we made full use of the local and global spatial information of the image pairs and proposed a dual-threshold matching algorithm based on the misalignment matrix to screen the initial matching results generated by the maximum normalized cross correlation. Under the premise of ensuring matching precision, the number of correctly matched point pairs is effectively increased to provide more sufficient samples for subsequent processing. Finally, we used a shallow neural network to establish the transformation relationship between the GSMS image and the reference image and resampled the GSMS image. We selected observations from five different periods of FY-4A/Advanced Geosynchronous Radiation Imager (AGRI) on-orbit and conducted two verification experiments: 1) in the image matching, compared with several commonly used algorithms, we found that the proposed matching algorithm has obvious advantages in matching precision and relative recall; and 2) in the image correction, the positioning error corrected by our methods is about 1.26 pixels <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\left ({3\sigma }\right)$ </tex-math></inline-formula> in the central area and about 1.30 pixels <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\left ({3\sigma }\right)$ </tex-math></inline-formula> in the edge area, which is about 14.9% and 9.1% better than the weighted iterative cubic polynomial fitting algorithm, respectively, with better robustness. In conclusion, the landmark-based geometric precision correction process proposed effectively improves the geometric accuracy of GSMS images, which is an important foundation for subsequent quantitative applications.

Single object tracking algorithm in occlusion scene based on improved ECO

To alleviate the occlusion problem in a single object tracking scene, this paper proposes an ECO-MHDU object tracking algorithm with a more powerful anti-occlusion performance based on the ECO tracker. The algorithm first uses the pre-trained MobileNetV3 lightweight backbone network on the ImageNet dataset to replace the ResNet network in the ECO to increase the speed of the algorithm to obtain the shallow and deep feature information of the image, while effectively using the attention mechanism in the MobileNetV3 network to strengthen the algorithm’s ability to extract target features; secondly, use the DropBlock operation on the acquired feature map to generate a random continuous mask on the feature map channel to improve the algorithm’s learning of the global robust spatial structure information; finally, a confidence update strategy is introduced into the GMM sample generation space. To improve the quality of training samples, unreliable tracking states such as confidence detection and occlusion are designed to avoid updating the sample space with damaging information. Compared with the ECO algorithm, the ECO-MHDU algorithm proposed in this paper has a success rate of 68.0% on the occlusion attributes of the OTB100 dataset, which is 2.3% higher than the ECO algorithm, and the ECO-MHDU algorithm also showed the best performance on the entire dataset sequence, with a success rate of 69.3%.

A Hierarchical Feature Extraction Network for Fast Scene Segmentation.

Semantic segmentation is one of the most active research topics in computer vision with the goal to assign dense semantic labels for all pixels in a given image. In this paper, we introduce HFEN (Hierarchical Feature Extraction Network), a lightweight network to reach a balance between inference speed and segmentation accuracy. Our architecture is based on an encoder-decoder framework. The input images are down-sampled through an efficient encoder to extract multi-layer features. Then the extracted features are fused via a decoder, where the global contextual information and spatial information are aggregated for final segmentations with real-time performance. Extensive experiments have been conducted on two standard benchmarks, Cityscapes and Camvid, where our network achieved superior performance on NVIDIA 2080Ti.

Video quality assessment with dense features and ranking pooling

Benefiting with the rapid development of communication networks, effective video quality assessment (VQA) models which provide guidance for video transmission and compression technologies are highly demanded. This paper proposes a general-purpose full-reference VQA method combining DenseNet with spatial pyramid pooling and RankNet to not only extract high-level distortion representation and global spatial information of samples but also characterize the temporal correlation among frames. Firstly, the pretrained DenseNet is modified and finetuned to extract high-level features of distorBenefiting with the rapid development of communication networks, effective video quality assessment (VQA) models which provide guidance for video transmission and compression technologies are highly demanded. This paper proposes a general-purpose full-reference VQA method combining DenseNet with spatial pyramid pooling and RankNet to not only extract high-level distortion representation and global spatial information of samples but also characterize the temporal correlation among frames. Firstly, the pretrained DenseNet is modified and finetuned to extract high-level features of distorted videos. Then, spatial pyramid pooling is equipped in the DenseNet module to process flexible inputs with arbitrary spatial resolution. Thus, this kind of input which has the same spatial resolution as the original distorted video is processed by the well-trained DenseNet to generate frame-level quality, which considers the global spatial information of videos directly. Finally, learning to rank is introduced to explore the high-level temporal correlation of distorted videos by taking the RankNet as the temporal pooling function. The experimental results on two public VQA databases show that the proposed algorithm performs consistently with human visual perception.

Multi-Scale Object Detection Method Based on Multi-Branch Parallel Dilated Convolution

<p indent=0mm>Existing object detection algorithms only use a fixed size convolution kernel when extracting features, ignoring the difference in the receptive field of different scale features, which affects the detection effect of different scale objects. To solve this problem, a multi-scale object detection network based on multi-branch parallel dilated convolution is proposed. Firstly, the basic network VGG-16 is used to extract the features of the image. Secondly, a multi-branch parallel dilated convolution is designed to extract multi-scale features to improve object detection ability of the network. Then, a non-local block is employed to integrate the global spatial information and enhance the context information. Finally, the object detection and location tasks are performed on feature maps with different scales. Experimental results on PASCAL VOC and MS COCO datasets demonstrate that the proposed method can effectively improve the detection accuracy of different scale objects and clearly improve the detection accuracy of small objects.

MS-AFF: a novel semantic segmentation approach for buried object based on multi-scale attentional feature fusion

Infrared technology is widely used in buried object detection since it can capture the heat radiated outward from the target objects. Compared to the visible images, infrared images present poor resolution, low contrast, and fuzzy visual effect, making it challenging to detect the target objects, specifically in complex backgrounds. In recent years, deep learning-based methods have made significant improvements in detection tasks. However, infrared images of buried objects are difficult to obtain. Less training samples, worse performance of deep-learning based detection. We raise a multi-scale attentional feature fusion module for infrared image semantic segmentation to solve this problem. Precisely, we integrate a series of feature maps from different levels by an atrous spatial pyramid structure. In this way, the model can obtain rich representation ability on the infrared images. Besides, a global spatial information attention module is employed to let the model focus on the target region and reduce disturbance in infrared images’ background. In addition, we propose an infrared segmentation dataset based on the infrared thermal imaging system. Finally, we use state-of-the-art object detection methods to train the buried object dataset and compare them with our proposed method. Extensive experiments on infrared segmentation dataset demonstrate the superiority of our method.