Enhancing object detection in aerial images

Pandey, Vishal; Anand, Khushboo; Kalra, Anmol; Gupta, Anmol; Roy, Partha Pratim; Kim, Byung-Gyu

doi:10.3934/mbe.2022370

Cited by 10 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to improving the model, Vishal Pandey et al [21] addressed the issue of dataset class imbalance through data augmentation techniques. They performed 90 • , 180 • , and 270 • rotations on infrequent classes, which helped to reduce the difference between minority and majority classes.…”

Section: Related Workmentioning

confidence: 99%

IEC-YOLOX:A Lightweight Object Detection Algorithm for UAV Target Detection

Song

Xue

et al. 2023

Preprint

View full text Add to dashboard Cite

Recently, unmanned aerial vehicles (UAVs) have been widely used in industries such as transportation and agriculture for capturing scenes. Aerial images taken by UAVs are one of the most widely used scenario for object detection applications. However, since UAV images are captured from high altitude, the target scale of UAV images is inconsistent compared with ordinary images as the background is more complex and the target size is smaller. To address this problem, we proposed a new network model IEC-YOLOX, which is based on YOLOX. The model adds a detection layer to YOLOX-tiny to enable the detection of small targets and utilizes iAFF to fuse features of different scales. The backbone network CSPDarknet is replaced with Extended-ELAN, which reduces the number of parameters by one-fifth. Additionally, a lightweight attention mechanism called CBAM is added to the new backbone network.This paper uses VisDrone 2019 as the experimental data. The result of our YOLOX-tiny network structure's mAP@50 is 35.3$\%$, and the number of parameters is 4.29M, which is about 4.3$\%$ higher than the baseline model (YOLOX-tiny) in terms of mAP@50, and the number of parameters has been reduced by 0.74M.

show abstract

Section: Related Workmentioning

confidence: 99%

IEC-YOLOX:A Lightweight Object Detection Algorithm for UAV Target Detection

Song

Xue

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…To improve the imbalance in category distribution, Li et al [30] proposed a new definition for positive samples and data augmentation algorithms, ameliorating the imbalance between vehicle targets and the background as well as among vehicle samples. Pandey et al [31] selected images with less frequent category occurrences and expanded them back into the dataset through rotation.…”

Section: Introductionmentioning

confidence: 99%

Vehicle Detection in UAV Images via Background Suppression Pyramid Network and Multi-Scale Task Adaptive Decoupled Head

Pan,

Xia,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Vehicle detection based on unmanned aerial vehicle (UAV) aerial images plays a significant role in areas such as traffic monitoring and management, disaster relief, and more, garnering extensive attention from researchers in recent years. However, datasets acquired from UAV platforms inevitably suffer from issues such as imbalanced class distribution, severe background interference, numerous small objects, and significant target scale variance, presenting substantial challenges to practical vehicle detection applications based on this platform. Addressing these challenges, this paper proposes an object detection model grounded in a background suppression pyramid network and multi-scale task adaptive decoupled head. Firstly, the model implements a long-tail feature resampling algorithm (LFRA) to solve the problem of imbalanced class distribution in the dataset. Next, a background suppression pyramid network (BSPN) is integrated into the Neck segment of the model. This network not only reduces the interference of redundant background information but also skillfully extracts features of small target vehicles, enhancing the ability of the model to detect small objects. Lastly, a multi-scale task adaptive decoupled head (MTAD) with varied receptive fields is introduced, enhancing detection accuracy by leveraging multi-scale features and adaptively generating relevant features for classification and detection. Experimental results indicate that the proposed model achieves state-of-the-art performance on lightweight object detection networks. Compared to the baseline model PP-YOLOE-s, our model improves the AP50:95 on the VisDrone-Vehicle dataset by 1.9%.

show abstract

“…Object detection has seen significant progress over the last several years [1][2][3][4][5][6][7]. Each new iteration or approach promises higher accuracy at the cost of more inference latency or less latency at the cost of lower accuracy when compared with the high-latency counterparts.…”

Section: Introductionmentioning

confidence: 99%

Motion Vector Extrapolation for Video Object Detection

True

Khan

2023

J. Imaging

View full text Add to dashboard Cite

Despite the continued successes of computationally efficient deep neural network architectures for video object detection, performance continually arrives at the great trilemma of speed versus accuracy versus computational resources (pick two). Current attempts to exploit temporal information in video data to overcome this trilemma are bottlenecked by the state of the art in object detection models. This work presents motion vector extrapolation (MOVEX), a technique which performs video object detection through the use of off-the-shelf object detectors alongside existing optical flow-based motion estimation techniques in parallel. This work demonstrates that this approach significantly reduces the baseline latency of any given object detector without sacrificing accuracy performance. Further latency reductions up to 24 times lower than the original latency can be achieved with minimal accuracy loss. MOVEX enables low-latency video object detection on common CPU-based systems, thus allowing for high-performance video object detection beyond the domain of GPU computing.

show abstract

Enhancing object detection in aerial images

Cited by 10 publications

References 27 publications

IEC-YOLOX:A Lightweight Object Detection Algorithm for UAV Target Detection

IEC-YOLOX:A Lightweight Object Detection Algorithm for UAV Target Detection

Vehicle Detection in UAV Images via Background Suppression Pyramid Network and Multi-Scale Task Adaptive Decoupled Head

Motion Vector Extrapolation for Video Object Detection

Contact Info

Product

Resources

About