Small Object Detection in Optical Remote Sensing Images via Modified Faster R-CNN

Ren, Yun; Zhu, Chenchen; Xiao, Shunping

doi:10.3390/app8050813

Cited by 222 publications

(123 citation statements)

References 29 publications

Supporting

Mentioning

122

Contrasting

Order By: Relevance

“…This deletes most of the cobbles and fine boulder information from the data if large scale mosaics were fed directly into the network. Hence, the smaller tiles exported from the backscatter mosaics were upscaled to values between 300 and 1200 pixels, which is the simplest approach to facilitate small object detection [30,31]. The size of anchor boxes used to determine the bounding box of objects were left at their standard settings of 32, 64, 128, For classification and object detection, we use an open source RetinaNet [27] implementation in Python, available on GitHub (https://github.com/fizyr/keras-retinanet, last accessed on 6 February 2019).…”

Section: Preparation Of Train Validation and Test Datasetsmentioning

confidence: 99%

“…Therefore, it is mandatory to detect objects of the smallest possible size and to consider the minimum object size detectable by the trained models. The minimum size of objects whose detection can be trained by RetinaNet depends on a) the resolution of the input backscatter mosaic and b) the minimum anchor box of the network measured in pixels multiplied by the threshold of areal overlap of 0.5 required for a positive training [30,31]. For a minimum anchor box of 32 pixels, this results in a theoretical minimum threshold for positive training of 23 × 23 pixels.…”

Section: Constraining the Minimum Size Of Detected Bouldersmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Boulders in Side Scan Sonar Mosaics by a Neural Network

Feldens

Darr

Feldens³

et al. 2019

Geosciences

View full text Add to dashboard Cite

Boulders provide ecologically important hard grounds in shelf seas, and form protected habitats under the European Habitats Directive. Boulders on the seafloor can usually be recognized in backscatter mosaics due to a characteristic pattern of high backscatter intensity followed by an acoustic shadow. The manual identification of boulders on mosaics is tedious and subjective, and thus could benefit from automation. In this study, we train an object detection framework, RetinaNet, based on a neural network backbone, ResNet, to detect boulders in backscatter mosaics derived from a sidescan-sonar operating at 384 kHz. A training dataset comprising 4617 boulders and 2005 negative examples similar to boulders was used to train RetinaNet. The trained model was applied to a test area located in the Kriegers Flak area (Baltic Sea), and the results compared to mosaic interpretation by expert analysis. Some misclassification of water column noise and boundaries of artificial plough marks occurs, but the results of the trained model are comparable to the human interpretation. While the trained model correctly identified a higher number of boulders, the human interpreter had an advantage at recognizing smaller objects comprising a bounding box of less than 7 × 7 pixels. Almost identical performance between the best model and expert analysis was found when classifying boulder density into three classes (0, 1-5, more than 5) over 10,000 m 2 areas, with the best performing model reaching an agreement with the human interpretation of 90%.

show abstract

Section: Preparation Of Train Validation and Test Datasetsmentioning

confidence: 99%

Section: Constraining the Minimum Size Of Detected Bouldersmentioning

confidence: 99%

Detection of Boulders in Side Scan Sonar Mosaics by a Neural Network

Feldens

Darr

Feldens³

et al. 2019

Geosciences

View full text Add to dashboard Cite

show abstract

“…Two-stage method originated from R-CNN [33], then successively arise Fast R-CNN [34] and Faster R-CNN [28]. R-CNN is the first object detection framework based on deep convolutional neural networks [35], which uses the selective search algorithm (SS) to extract the candidate regions and computes features by CNN. A set of class-specific linear SVMs [36] and regressors are used to classify and fine-tune the bounding boxes, respectively.…”

Section: Introductionmentioning

confidence: 99%

A Coarse-to-Fine Network for Ship Detection in Optical Remote Sensing Images

Gong

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

With the increasing resolution of optical remote sensing images, ship detection in optical remote sensing images has attracted a lot of research interests. The current ship detection methods usually adopt the coarse-to-fine detection strategy, which firstly extracts low-level and manual features, and then performs multi-step training. Inadequacies of this strategy are that it would produce complex calculation, false detection on land and difficulty in detecting the small size ship. Aiming at these problems, a sea-land separation algorithm that combines gradient information and gray information is applied to avoid false alarms on land, the feature pyramid network (FPN) is used to achieve small ship detection, and a multi-scale detection strategy is proposed to achieve ship detection with different degrees of refinement. Then the feature extraction structure is adopted to fuse different hierarchical features to improve the representation ability of features. Finally, we propose a new coarse-to-fine ship detection network (CF-SDN) that directly achieves an end-to-end mapping from image pixels to bounding boxes with confidences. A coarse-to-fine detection strategy is applied to improve the classification ability of the network. Experimental results on optical remote sensing image set indicate that the proposed method outperforms the other excellent detection algorithms and achieves good detection performance on images including some small-sized ships and dense ships near the port.

show abstract

“…Region proposal-based detection networks have been extensively applied in the target detection field, including Region-Convolutional Neural Networks (R-CNN) [16], Fast-Region Convolutional Neural Networks (Fast-RCNN) [17], and Faster-Region Convolutional Neural Networks (Faster-RCNN) [18]. Through analyzing these works, scientists put forward some small target detection algorithms [19][20][21]. Moreover, Cai et al [14] proposed a Multi-scale Deep Convolutional Neural Network (MS-CNN) which predicts objects at different layers of the feature hierarchy.…”

Section: Introductionmentioning

confidence: 99%

Visual Detail Augmented Mapping for Small Aerial Target Detection

Dai

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Moving target detection plays a primary and pivotal role in avionics visual analysis, which aims to completely and accurately detect moving objects from complex backgrounds. However, due to the relatively small sizes of targets in aerial video, many deep networks that achieve success in normal size object detection are usually accompanied by a high rate of false alarms and missed detections. To address this problem, we propose a novel visual detail augmented mapping approach for small aerial target detection. Concretely, we first present a multi-cue foreground segmentation algorithm including motion and grayscale information to extract potential regions. Then, based on the visual detail augmented mapping approach, the regions that might contain moving targets are magnified to multi-resolution to obtain detailed target information and rearranged into new foreground space for visual enhancement. Thus, original small targets are mapped to a more efficient foreground augmented map which is favorable for accurate detection. Finally, driven by the success of deep detection network, small moving targets can be well detected from aerial video. Experiments extensively demonstrate that the proposed method achieves success in small aerial target detection without changing the structure of the deep network. In addition, compared with the-state-of-art object detection algorithms, it performs favorably with high efficiency and robustness.

show abstract

Small Object Detection in Optical Remote Sensing Images via Modified Faster R-CNN

Cited by 222 publications

References 29 publications

Detection of Boulders in Side Scan Sonar Mosaics by a Neural Network

Detection of Boulders in Side Scan Sonar Mosaics by a Neural Network

A Coarse-to-Fine Network for Ship Detection in Optical Remote Sensing Images

Visual Detail Augmented Mapping for Small Aerial Target Detection

Contact Info

Product

Resources

About