Infrared Small Object Detection Using Deep Interactive U-Net

Wu, X.; Hong, Danfeng; Huang, Zhanchao; Chanussot, Jocelyn

doi:10.1109/lgrs.2022.3218688

Cited by 15 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm improved the robustness of the model in detecting small targets by constructing a multimodal feature extraction module, weighting and fusing the modal features, and acquiring the semantic features of small targets by introducing a double attention module. Wu et al [ 22 ] introduced an algorithm with U-shaped structure named ISTDU-Net, which was designed for detecting infrared small targets. The algorithm enhanced the weight of small targets by introducing feature map group perception, while incorporating a fully connected layer into the jump connection to enhance the discernibility between the target and the background.…”

Section: Related Workmentioning

confidence: 99%

YOLO-B:An infrared target detection algorithm based on bi-fusion and efficient decoupled

Hou,

Tang,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The YOLO-B infrared target detection algorithm is proposed to address the problems of incomplete extraction of detailed features and missed and wrong detection of infrared targets by YOLOv5s. The algorithm improves the SPPF of YOLOv5s feature extraction network by proposing the CSPPF structure to increase the sensory field of the model. The Bifusion Neck structure is invoked to fuse the shallow location information with deep semantic information to enhance the feature extraction capability of the model. Taking fully into account the different information of concern for classification and localization, the efficient decoupled head is used as the prediction head of this algorithm, which reduces the latency while maintaining the accuracy. WIoUv3 loss is used as a bounding box regression loss function to reduce the harmful gradient generated by low-quality examples and reduce the competitiveness of high-quality anchor frames. Comparative experiments were conducted for each of the four improvement points, and the experimental results showed that each improvement point had the highest detection accuracy in the comparative experiments of the same category. All improvement points are fused in turn and ablation experiments are performed. The YOLO-B algorithm improves 1.9% in accuracy, 7.3% in recall, 3.8% in map_0.5, and 4.6% in map_0.5:0.95 compared to YOLOv5s. When compared with YOLOv7 and YOLOv8s, the proposed algorithm has better performance in terms of the number of parameters and detection accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

YOLO-B:An infrared target detection algorithm based on bi-fusion and efficient decoupled

Hou,

Tang,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Adding upsampling layers in very deep convolutional networks for large-scale image recognition (VGG) can provide more accurate semantic segmentation results on less training data. U-Net architecture constructs the connections between its upsampling layer and the corresponding feature layer in the classification network [53,54]. A CNN was initially used to solve the image classification problem.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

A Single Data Extraction Algorithm for Oblique Photographic Data Based on the U-Net

Wang,

Li,

Lin

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

In the automated modeling generated by oblique photography, various terrains cannot be physically distinguished individually within the triangulated irregular network (TIN). To utilize the data representing individual features, such as a single building, a process of building monomer construction is required to identify and extract these distinct parts. This approach aids subsequent analyses by focusing on specific entities, mitigating interference from complex scenes. A deep convolutional neural network is constructed, combining U-Net and ResNeXt architectures. The network takes as input both digital orthophoto map (DOM) and oblique photography data, effectively extracting the polygonal footprints of buildings. Extraction accuracy among different algorithms is compared, with results indicating that the ResNeXt-based network achieves the highest intersection over union (IOU) for building segmentation, reaching 0.8255. The proposed “dynamic virtual monomer” technique binds the extracted vector footprints dynamically to the original oblique photography surface through rendering. This enables the selective representation and querying of individual buildings. Empirical evidence demonstrates the effectiveness of this technique in interactive queries and spatial analysis. The high level of automation and excellent accuracy of this method can further advance the application of oblique photography data in 3D urban modeling and geographic information system (GIS) analysis.

show abstract

“…In [39], a pyramid single-shot detector is proposed for small object detection in remote sensing images. To further enhance small object detection, in [40], an interactive U-Net architecture is proposed which has higher feature learning by utilising object's global context information. In [41], a detector is proposed that uses spatial-frequency channel features by incorporating both rotation-invariant channel features and original spatial channel features which enhances the system's robustness, and accuracy.…”

Section: A Object Detectionmentioning

confidence: 99%

Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery

Shamsolmoali

Zareapoor

Chanussot

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Efficient object detection methods have recently received great attention in remote sensing. Although deep convolutional networks often have excellent detection accuracy, their deployment on resource-limited edge devices is difficult. Knowledge distillation (KD) is a strategy for addressing this issue since it makes models lightweight while maintaining accuracy. However, existing KD methods for object detection have encountered two constraints. First, they discard potentially important background information and only distill nearby foreground regions. Second, they only rely on the global context, which limits the student detector's ability to acquire local information from the teacher detector. To address the aforementioned challenges, we propose Attention-based Feature Distillation (AFD), a new KD approach that distills both local and global information from the teacher detector. To enhance local distillation, we introduce a multi-instance attention mechanism that effectively distinguishes between background and foreground elements. This approach prompts the student detector to focus on the pertinent channels and pixels, as identified by the teacher detector. Local distillation lacks global information, thus attention global distillation is proposed to reconstruct the relationship between various pixels and pass it from teacher to student detector. The performance of AFD is evaluated on two public aerial image benchmarks, and the evaluation results demonstrate that AFD in object detection can attain the performance of other state-of-the-art models while being efficient.

show abstract

Infrared Small Object Detection Using Deep Interactive U-Net

Cited by 15 publications

References 19 publications

YOLO-B:An infrared target detection algorithm based on bi-fusion and efficient decoupled

YOLO-B:An infrared target detection algorithm based on bi-fusion and efficient decoupled

A Single Data Extraction Algorithm for Oblique Photographic Data Based on the U-Net

Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery

Contact Info

Product

Resources

About