An Efficient and Scene-Adaptive Algorithm for Vehicle Detection in Aerial Images Using an Improved YOLOv3 Framework

Zhang, Xunxun; Zhu, Xu

doi:10.3390/ijgi8110483

Cited by 11 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Zheng et al [22] augmented the training dataset with synthesized vehicle images and improved performance. Zhang et al [23] adopted the YOLOv3 framework and proposed a scene-adaptive feature map fusion algorithm for effective vehicle detection in video data.…”

Section: Vehicle Detection By Deep Learningmentioning

confidence: 99%

“…2020, 12, 575 4 of 24 and did not enhance the background features that would be significantly different in a different area. The method of Zhang et al [23] is expected to be relatively robust to image feature difference because their YOLOv3-based architecture includes FPN as a component, and FPN effectively captures semantic features that would be robust to low-level image feature differences. However, this is not a direct solution, and thus, it would not fully solve the problem (We will confirm this by using M2Det architecture in Section 4.6).…”

Section: Vehicle Detection By Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

A Method for Vehicle Detection in High-Resolution Satellite Images that Uses a Region-Based Object Detector and Unsupervised Domain Adaptation

Koga¹,

Miyazaki

Shibasaki

2020

Remote Sensing

View full text Add to dashboard Cite

Recently, object detectors based on deep learning have become widely used for vehicle detection and contributed to drastic improvement in performance measures. However, deep learning requires much training data, and detection performance notably degrades when the target area of vehicle detection (the target domain) is different from the training data (the source domain). To address this problem, we propose an unsupervised domain adaptation (DA) method that does not require labeled training data, and thus can maintain detection performance in the target domain at a low cost. We applied Correlation alignment (CORAL) DA and adversarial DA to our region-based vehicle detector and improved the detection accuracy by over 10% in the target domain. We further improved adversarial DA by utilizing the reconstruction loss to facilitate learning semantic features. Our proposed method achieved slightly better performance than the accuracy achieved with the labeled training data of the target domain. We demonstrated that our improved DA method could achieve almost the same level of accuracy at a lower cost than non-DA methods with a sufficient amount of labeled training data of the target domain.

show abstract

Section: Vehicle Detection By Deep Learningmentioning

confidence: 99%

Section: Vehicle Detection By Deep Learningmentioning

confidence: 99%

A Method for Vehicle Detection in High-Resolution Satellite Images that Uses a Region-Based Object Detector and Unsupervised Domain Adaptation

Koga¹,

Miyazaki

Shibasaki

2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…[69] Development of the Deep Vehicle Counting Framework based on Enhanced-SSD [70] Comparison between YOLOv3 (best model) and Faster R-CNN [71] Detection model based on two CNNs that adopt the VGG-16 model [72] EOVNet (Earth observation image-based vehicle detection network), a modified Faster R-CNN. [1] Improved Faster R-CNN with Multiscale Feature Fusion and Homography Augmentation [73] R3-Net a deep network for multi-oriented vehicle detection [74] Detection algorithm based on Faster R-CNN [75] Systematic investigation of the Fast R-CNN and Faster R-CNN in vehicle detection [5] YOLOv3, vehicle tracking using deep appearance features, and Kalman filtering for motion estimation [7] Model based on multi-task cost-sensitive-convolutional neural network (MTCS-CNN) [76] Novel double focal loss convolutional neural network (DFLCNN) [77] Improved YOLOv3 using a sloping bounding box attached to the angle of the target vehicles [78] Orientation-aware feature fusion single-stage detection (OAFF-SSD) [15] Detection model for different scales using CNN and proposition of an Outlier-Aware Non-Maximum Suppression. [79] Comparison among faster R-CNN, R-FCN, and SSD (Best model) [80] Optimized DL model considering feature extraction, object detection, and non-maximum suppression.…”

Section: Papermentioning

confidence: 99%

Bounding Box-Free Instance Segmentation Using Semi-Supervised Iterative Learning for Vehicle Detection

Carvalho

Albuquerque

Santana

et al. 2022

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

View full text Add to dashboard Cite

Vehicle classification is a hot computer vision topic, with studies ranging from ground-view to top-view imagery. Topview images allow understanding city patterns, traffic management, among others. However, there are some difficulties for pixel-wise classification: (a) most vehicle classification studies use object detection methods, and most publicly available datasets are designed for this task, (b) creating instance segmentation datasets is laborious, and (c) traditional instance segmentation methods underperform on this task since the objects are small. Thus, the present research objectives are: (1) propose a novel semi-supervised iterative learning approach using GIS software, (2) propose a box-free instance segmentation approach, and (3) provide a city-scale vehicle dataset. The iterative learning procedure considered: (1) labeling a few vehicles from the entire scene, (2) choosing training samples near those areas, ( 3) training the DL model (U-net with Efficient-net-B7 backbone), (4) classifying the whole scene, (5) converting the predictions into shapefile, (6) correcting areas with wrong predictions, (7) including them in the training data, (8) repeating until results are satisfactory. We considered vehicle interior and borders to separate instances using a semantic segmentation model. When removing the borders, the vehicle interior becomes isolated, allowing for unique object identification. Our procedure is very efficient and accurate for generating data iteratively, which resulted in 122,567 mapped vehicles. Metrics-wise, our method presented higher IoU when compared to box-based methods (82% against 72%), and per-object metrics surpassed 90% for precision and recall.

show abstract

“…Won et al proposed increasing the recognition speed by decreasing the Darknet-53 to 24 layers [ 34 ]. Zhang and Zhu introduced the sloping anchor box to overcome the flaws of the traditional horizontal bounding box, which is intended to predict the target position and angle [ 35 ].…”

Section: Related Workmentioning

confidence: 99%

A PCB Electronic Components Detection Network Design Based on Effective Receptive Field Size and Anchor Size Matching

Chen

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Vision-based recognizing and positioning of electronic components on the PCB (printed circuit board) can improve the quality inspection efficiency of electronic products in the manufacturing process. With the improvement of the design and the production process, the electronic components on the PCB show the characteristics of small sizes and similar appearances, which brings challenges to visual object detection. This paper designs a real-time electronic component detection network through effective receptive field size and anchor size matching in YOLOv3. We make contributions in the following three aspects: (1) realizing the calculation and visualization of the effective receptive field size of the different depth layers of the CNN (convolutional neural network) based on gradient backpropagation; (2) proposing a modular YOLOv3 composition strategy that can be added and removed; and (3) designing a lightweight and efficient detection network by effective receptive field size and anchor size matching algorithm. Compared with the Faster-RCNN (regions with convolutional neural network) features, SSD (single-shot multibox detectors), and original YOLOv3, our method not only has the highest detection mAP (mean average precision) on the PCB electronic component dataset, which is 95.03%, the smallest parameter size of the memory, about 1/3 of the original YOLOv3 parameter amount, but also the second-best performance on FLOPs (floating point operations).

show abstract

An Efficient and Scene-Adaptive Algorithm for Vehicle Detection in Aerial Images Using an Improved YOLOv3 Framework

Cited by 11 publications

References 24 publications

A Method for Vehicle Detection in High-Resolution Satellite Images that Uses a Region-Based Object Detector and Unsupervised Domain Adaptation

A Method for Vehicle Detection in High-Resolution Satellite Images that Uses a Region-Based Object Detector and Unsupervised Domain Adaptation

Bounding Box-Free Instance Segmentation Using Semi-Supervised Iterative Learning for Vehicle Detection

A PCB Electronic Components Detection Network Design Based on Effective Receptive Field Size and Anchor Size Matching

Contact Info

Product

Resources

About