ABNet: Adaptive Balanced Network for Multiscale Object Detection in Remote Sensing Imagery

Liu, Yanfeng; Li, Qiang; Yuan, Yuan; Du, Qian; Wang, Qi

doi:10.1109/tgrs.2021.3133956

Cited by 112 publications

(31 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a multi-scale information preservation module, Han et al [39] constructed multi-scale pyramid images and features for each image to retain as much multi-scale information of the input data as possible, which is helpful to achieve better performance of object detection. To adaptively combine multi-scale feature information on different channels and spatial positions, FPN was used to obtain more discriminative features and achieve an efficient fusion of multi-scale features in [40]. In addition, the dilated/deformable convolution kernel [41,42] was used to expand the receptive field of algorithms without loss of resolution to achieve multi-scale object detection.…”

Section: A Cnn-based Object Detectionmentioning

confidence: 99%

A CNN-Transformer Hybrid Model Based on CSWin Transformer for UAV Image Object Detection

Lan

Niu

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The object detection of unmanned aerial vehicle (UAV) images has widespread applications in numerous fields; however, the complex background, diverse scales, and uneven distribution of objects in UAV images make object detection a challenging task. This study proposes a convolution neural network (CNN)-transformer hybrid model to achieve efficient object detection in UAV images, which has three advantages that contribute to improving the object detection performance. First, the efficient and effective cross-shaped window (CSWin) transformer can be used as a backbone to obtain image features at different levels, and the obtained features can be input into the feature pyramid network (FPN) to achieve multi-scale representation, which will contribute to multi-scale object detection. Second, a hybrid patch embedding module is constructed to extract and utilize low-level information such as the edges and corners of the image. Finally, a slicing-based inference method is constructed to fuse the inference results of the original image and sliced images, which will improve the small object detection accuracy without modifying the original network. Experimental results on public datasets illustrate that the proposed method can improve the performance more effectively than several popular and state-of-the-art object detection methods.

show abstract

Section: A Cnn-based Object Detectionmentioning

confidence: 99%

A CNN-Transformer Hybrid Model Based on CSWin Transformer for UAV Image Object Detection

Lan

Niu

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The continuous improvement of computing power has made data-driven deep learning methods appear on the stage of history, bringing about a series of excellent algorithms. Deep learning-based methods show superior performance over traditional algorithms in many computer vision fields ( Hu et al, 2021 ; Liu et al, 2021b ; Teng et al, 2021 ; Zhao et al, 2021 ). The current mainstream object detection methods can be classified into Anchor-based methods and Anchor-free methods according to whether candidate regions are generated, with the main difference being whether target regression and classification are performed by predefined anchor frames.…”

Section: Related Workmentioning

confidence: 99%

Lightweight and efficient neural network with SPSA attention for wheat ear detection

Dong

Liu

Kang

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

Advancements in deep neural networks have made remarkable leap-forwards in crop detection. However, the detection of wheat ears is an important yet challenging task due to the complex background, dense targets, and overlaps between wheat ears. Currently, many detectors have made significant progress in improving detection accuracy. However, some of them are not able to make a good balance between computational cost and precision to meet the needs of deployment in real world. To address these issues, a lightweight and efficient wheat ear detector with Shuffle Polarized Self-Attention (SPSA) is proposed in this paper. Specifically, we first utilize a lightweight backbone network with asymmetric convolution for effective feature extraction. Next, SPSA attention is given to adaptively select focused positions and produce a more discriminative representation of the features. This strategy introduces polarized self-attention to spatial dimension and channel dimension and adopts Shuffle Units to combine those two types of attention mechanisms effectively. Finally, the TanhExp activation function is adopted to accelerate the inference speed and reduce the training time, and CIOU loss is used as the border regression loss function to enhance the detection ability of occlusion and overlaps between targets. Experimental results on the Global Wheat Head Detection dataset show that our method achieves superior detection performance compared with other state-of-the-art approaches.

show abstract

“…However, due to the doubling of the number of anchor points, the model's efficiency is low. Liu et al [37] improve the feature representation ability of the backbone, adaptively combining multiscale features, and effectively reducing the interference of the background to the object, but this method has little effect on small objects. Thus, most of these methods require a deep network structure to extract high-level semantic information, leading to a lack of low-level information for re-identification.…”

Section: A Object Detectionmentioning

confidence: 99%

Dual-Attention-Driven Multiscale Fusion Object Searching Network for Remote Sensing Imagery

Duan

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Object search is a challenging yet important task. Many efforts have been made to address this issue and achieve great progress in natural image, yet searching all specified types of objects from remote sensing image is barely studied. In this work, we are interested in searching objects from remote sensing images. Compared to person search in natural scenes, this task is challenging in two factors: One is that remote image usually contains a large number of objects, which poses a great challenge to characterize the object features. Another is that the objects in remote sensing images are dense, which easily yields erroneous localization. To address these issues, we propose a new end-toend deep learning framework for object search in remote sensing images. First, we propose a multi-scale feature aggregation (MSFA) module, which strengthens the representation of lowlevel features by fusing multi-layer features. The fused features with richer details significantly improve the accuracy of object search. Second, we propose a dual-attention object enhancement (DAOE) module to enhance features from channel and spatial dimensions. The enhanced features significantly improve the localization accuracy for dense objects. Finally, we built two challenging datasets based on the remote sensing images, which contains complex changes in space and time. The experiments and comparisons demonstrate the state-of-the-art performance of our method on the challenging datasets.

show abstract

ABNet: Adaptive Balanced Network for Multiscale Object Detection in Remote Sensing Imagery

Cited by 112 publications

References 56 publications

A CNN-Transformer Hybrid Model Based on CSWin Transformer for UAV Image Object Detection

A CNN-Transformer Hybrid Model Based on CSWin Transformer for UAV Image Object Detection

Lightweight and efficient neural network with SPSA attention for wheat ear detection

Dual-Attention-Driven Multiscale Fusion Object Searching Network for Remote Sensing Imagery

Contact Info

Product

Resources

About