Cropping Region Proposal Network Based Framework for Efficient Object Detection on Large Scale Remote Sensing Images

Lin, Qifeng; Zhao, Jianhui; Tong, Qianqian; Zhang, Guian; Yuan, Zhiyong; Fu, Gang

doi:10.1109/icme.2019.00265

Cited by 3 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The purposes of previous works on the region proposal methods can be viewed from two aspects. First, object detection needs to be conducted on certain areas excluding the massive backgrounds with very little chance of target objects being present [14,29]. Secondly, because objects taken in the aerial images are very small in pixels and distributed sparsely and non-uniformly, e.g., pedestrians or vehicles, object detectors can show improvement by re-executing object detection especially in zoom-out images whose target objects are densely crowded [16,30].…”

Section: Region Proposal Methods For Aerial Imagesmentioning

confidence: 99%

“…For the former purpose, the work in [14] proposed a Cropping Region Proposal Network (CRPN), which exploits a weak semantic RPN quickly searching for candidate object proposals and unites neighboring objects based on Intersection-over-Union (IoU). The other work sharing the same purpose [29] predicted whether objects exist or not for a patch image generated by a sliding-window fashion.…”

Section: Region Proposal Methods For Aerial Imagesmentioning

confidence: 99%

“…Figure 2 provides two examples of actual remote sensing images taken from harbor-peripheral areas, where the ship objects are sparsely distributed in the aerial images. Inspired by this motivation, some researchers have been presented the region proposal methods for selectively analyzing regions on vast areas [14,15]. CRPN [14] generates the cropping regions by uniting boundaries of inferred object proposals, and CPNet [16] infers the candidate region proposals, trained with cluster groundtruth annotations generated by mean-shift algorithm [15].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hierarchical Multi-Label Object Detection Framework for Remote Sensing Images

Shin

Kim

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Detecting objects such as aircraft and ships is a fundamental research area in remote sensing analytics. Owing to the prosperity and development of CNNs, many previous methodologies have been proposed for object detection within remote sensing images. Despite the advance, using the object detection datasets with a more complex structure, i.e., datasets with hierarchically multi-labeled objects, is limited to the existing detection models. Especially in remote sensing images, since objects are obtained from bird’s-eye view, the objects are captured with restricted visual features and not always guaranteed to be labeled up to fine categories. We propose a hierarchical multi-label object detection framework applicable to hierarchically partial-annotated datasets. In the framework, an object detection pipeline called Decoupled Hierarchical Classification Refinement (DHCR) fuses the results of two networks: (1) an object detection network with multiple classifiers, and (2) a hierarchical sibling classification network for supporting hierarchical multi-label classification. Our framework additionally introduces a region proposal method for efficient detection on vain areas of the remote sensing images, called clustering-guided cropping strategy. Thorough experiments validate the effectiveness of our framework on our own object detection datasets constructed with remote sensing images from WorldView-3 and SkySat satellites. Under our proposed framework, DHCR-based detections significantly improve the performance of respective baseline models and we achieve state-of-the-art results on the datasets.

show abstract

Section: Region Proposal Methods For Aerial Imagesmentioning

confidence: 99%

Section: Region Proposal Methods For Aerial Imagesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Multi-Label Object Detection Framework for Remote Sensing Images

Shin

Kim

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The Faster R-CNN [14] with Feature Pyramid Network [16] is widely used as a two-stage method in common object detection. Nevertheless, remote sensing objects are smaller, denser, and positioned at various angles [17,18]. Moreover, different from the horizontal bounding box in common detection, remote sensing detection usually uses an oriented bounding box to capture objects more tightly.…”

Section: Remote Sensing Object Detectionmentioning

confidence: 99%

HVConv: Horizontal and Vertical Convolution for Remote Sensing Object Detection

Chen,

Lin,

Huang

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Generally, the interesting objects in aerial images are completely different from objects in nature, and the remote sensing objects in particular tend to be more distinctive in aspect ratio. The existing convolutional networks have equal aspect ratios of the receptive fields, which leads to receptive fields either containing non-relevant information or being unable to fully cover the entire object. To this end, we propose Horizontal and Vertical Convolution, which is a plug-and-play module to address different aspect ratio problems. In our method, we introduce horizontal convolution and vertical convolution to expand the receptive fields in the horizontal and vertical directions, respectively, to reduce redundant receptive fields, so that remote sensing objects with different aspect ratios can achieve better receptive fields coverage, thereby achieving more accurate feature representation. In addition, we design an attention module to dynamically aggregate these two sub-modules to achieve more accurate feature coverage. Extensive experimental results on the DOTA and HRSC2016 datasets show that our HVConv achieves accuracy improvements in diverse detection architectures and obtains SOTA accuracy (mAP score of 77.60% with DOTA single-scale training and mAP score of 81.07% with DOTA multi-scale training). Various ablation studies were conducted as well, which is enough to verify the effectiveness of our model.

show abstract

“…Lin et al introduced Cropping Region Proposal Network (CRPN), a novel framework designed to improve object detection efficiency in large-scale remote sensing images [87]. It comprised a weak semantic RPN for rapid identification of interesting regions and applied a dual-scale strategy to generate effective cropping regions.…”

Section: ) Rpn Simplificationmentioning

confidence: 99%

Near-Edge Computing Aware Object Detection: A Review

Setyanto,

Sasongko,

Fikri

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Cropping Region Proposal Network Based Framework for Efficient Object Detection on Large Scale Remote Sensing Images

Cited by 3 publications

References 13 publications

Hierarchical Multi-Label Object Detection Framework for Remote Sensing Images

Hierarchical Multi-Label Object Detection Framework for Remote Sensing Images

HVConv: Horizontal and Vertical Convolution for Remote Sensing Object Detection

Near-Edge Computing Aware Object Detection: A Review

Contact Info

Product

Resources

About