YOLO-Fine: One-Stage Detector of Small Objects Under Various Backgrounds in Remote Sensing Images

Pham, Minh‐Tan; Courtrai, Luc; Friguet, Chloé; Lefèvre, Sébastien; Baussard, Alexandre

doi:10.3390/rs12152501

Cited by 111 publications

(61 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After removing the last residual unit of YOLO V3 body, it will not change the accuracy of the network for small target detection, and will accelerate the detection speed. We compared the method in this article with SEN [6], YOLO V5 [7] and YOLO-Fine [8], and the results proved the superiority of our method.…”

Section: Introductionmentioning

confidence: 73%

“…The authors of [19] examined the applicability of object proposal methods for vehicle detection in aerial images, and overcome drawbacks of the original Fast R-CNN and Faster R-CNN for small objects as in the case of aerial images by changing the scale and number of proposals. The authors of [8] proposed YOLO-Fine to be capable of detecting small objects. In essence, this method is one of all the experiments in this paper, such as Figure 3.…”

Section: Related Workmentioning

confidence: 99%

“…In essence, this method is one of all the experiments in this paper, such as Figure 3. And this method in [8] is straightforward and it is lack of theoretical analysis.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A New Method of Different Neural Network Depth and Feature Map Size on Remote Sensing Small Target Detection

Cao

Yang

Chen

2021

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have shown strong learning capabilities in computer vision tasks such as classification and detection. Especially with the introduction of excellent detection models such as YOLO (V1, V2 and V3) and Faster R-CNN, CNNs have greatly improved detection efficiency and accuracy. However, due to the special angle of view, small size, few features, and complicated background, CNNs that performs well in the ground perspective dataset, fails to reach a good detection accuracy in the remote sensing image dataset. To this end, based on the YOLO V3 model, we used feature maps of different depths as detection outputs to explore the reasons for the poor detection rate of small targets in remote sensing images by deep neural networks. We also analyzed the effect of neural network depth on small target detection, and found that the excessive deep semantic information of neural network has little effect on small target detection. Finally, the verification on the VEDAI dataset shows, that the fusion of shallow feature maps with precise location information and deep feature maps with rich semantics in the CNNs can effectively improve the accuracy of small target detection in remote sensing images.

show abstract

Section: Introductionmentioning

confidence: 73%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A New Method of Different Neural Network Depth and Feature Map Size on Remote Sensing Small Target Detection

Cao

Yang

Chen

2021

View full text Add to dashboard Cite

show abstract

“…Since the number of true negative objects (i.e., objects not part of the category of interest) is generally not defined, reporting a full confusion matrix and the associated OA metric is generally not possible. Nevertheless, reporting the number of TP, TN, FN, and FP, along with the derived accuracy measures typically used-precision, recall, and F1 (e.g., [80])-ensures clarity in the results.…”

Section: Object Detection and Instance Segmentationmentioning

confidence: 99%

Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies—Part 2: Recommendations and Best Practices

2021

View full text Add to dashboard Cite

Convolutional neural network (CNN)-based deep learning (DL) has a wide variety of applications in the geospatial and remote sensing (RS) sciences, and consequently has been a focus of many recent studies. However, a review of accuracy assessment methods used in recently published RS DL studies, focusing on scene classification, object detection, semantic segmentation, and instance segmentation, indicates that RS DL papers appear to follow an accuracy assessment approach that diverges from that of traditional RS studies. Papers reporting on RS DL studies have largely abandoned traditional RS accuracy assessment terminology; they rarely reported a complete confusion matrix; and sampling designs and analysis protocols generally did not provide a population-based confusion matrix, in which the table entries are estimates of the probabilities of occurrence of the mapped landscape. These issues indicate the need for the RS community to develop guidance on best practices for accuracy assessment for CNN-based DL thematic mapping and object detection. As a first step in that process, we explore key issues, including the observation that accuracy assessments should not be biased by the CNN-based training and inference processes that rely on image chips. Furthermore, accuracy assessments should be consistent with prior recommendations and standards in the field, should support the estimation of a population confusion matrix, and should allow for assessment of model generalization. This paper draws from our review of the RS DL literature and the rich record of traditional remote sensing accuracy assessment research while considering the unique nature of CNN-based deep learning to propose accuracy assessment best practices that use appropriate sampling methods, training and validation data partitioning, assessment metrics, and reporting standards.

show abstract

“…Since the YOLO network can recognize targets in the image without the requirement of the region proposal network by directly performing regression, this allows YOLO to perform much faster detection. Recently, the state-of-art version (YOLOv3) has been used to attain higher precision, accuracy and speed and optimize for the detection of small targets [ 21 ]. The original YOLOv3 network optimized its anchors for the head tracking part; the detection accuracy of passenger flow density in a metro system reached 95% [ 22 ].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Industry 4.0 and Internet of Things towards Effective Energy Management for Smart Buildings

Elsisi

Tran

Mahmoud

et al. 2021

Sensors

137

View full text Add to dashboard Cite

Worldwide, energy consumption and saving represent the main challenges for all sectors, most importantly in industrial and domestic sectors. The internet of things (IoT) is a new technology that establishes the core of Industry 4.0. The IoT enables the sharing of signals between devices and machines via the internet. Besides, the IoT system enables the utilization of artificial intelligence (AI) techniques to manage and control the signals between different machines based on intelligence decisions. The paper’s innovation is to introduce a deep learning and IoT based approach to control the operation of air conditioners in order to reduce energy consumption. To achieve such an ambitious target, we have proposed a deep learning-based people detection system utilizing the YOLOv3 algorithm to count the number of persons in a specific area. Accordingly, the operation of the air conditioners could be optimally managed in a smart building. Furthermore, the number of persons and the status of the air conditioners are published via the internet to the dashboard of the IoT platform. The proposed system enhances decision making about energy consumption. To affirm the efficacy and effectiveness of the proposed approach, intensive test scenarios are simulated in a specific smart building considering the existence of air conditioners. The simulation results emphasize that the proposed deep learning-based recognition algorithm can accurately detect the number of persons in the specified area, thanks to its ability to model highly non-linear relationships in data. The detection status can also be successfully published on the dashboard of the IoT platform. Another vital application of the proposed promising approach is in the remote management of diverse controllable devices.

show abstract

YOLO-Fine: One-Stage Detector of Small Objects Under Various Backgrounds in Remote Sensing Images

Cited by 111 publications

References 49 publications

A New Method of Different Neural Network Depth and Feature Map Size on Remote Sensing Small Target Detection

A New Method of Different Neural Network Depth and Feature Map Size on Remote Sensing Small Target Detection

Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies—Part 2: Recommendations and Best Practices

Deep Learning-Based Industry 4.0 and Internet of Things towards Effective Energy Management for Smart Buildings

Contact Info

Product

Resources

About