Design and Implementation of an Illegal Crop Object Detection System using Image Slicing and Transformer Techniques to High-Resolution Drone Data (고해상도 드론 데이터에 이미지 슬라이싱과 Transformer 기법을 적용한 불법작물 객체 탐지 시스템 설계 및 구현)

Hyun-Soo Kim (김현수); Lee Ye-Seul (이예슬); Shin DongMyung (신동명); Chan-jae Lee (이찬재); Myung-Ho Kim (김명호)

doi:10.29056/jsav.2023.3.09

Design and Implementation of an Illegal Crop Object Detection System using Image Slicing and Transformer Techniques to High-Resolution Drone Data

Journal of Software Assessment and Valuation
Abbr : JSAV
2023, 19(1), pp.69~76
DOI : 10.29056/jsav.2023.3.09
Publisher : Korea Software Assessment and Valuation Society
Research Area : Engineering > Computer Science
Received : March 10, 2023
Accepted : March 20, 2023
Published : March 31, 2023

Hyun-Soo Kim ¹, Lee Ye-Seul ¹, Shin DongMyung ², Chan-jae Lee ³, Myung-Ho Kim ⁴

¹엘에스웨어
²엘에스웨어 (주)
³오케스트로
⁴숭실대학교

Accredited

ABSTRACT

In this paper, we studied how to apply slicing techniques to 4K and 8K images using high-resolution drone data, and used them to detect and de-identify personal information objects (car, people), and designed and implemented a system that detects and visualizes illegal crop objects in de-identified images. For privacy object detection and de-identification, single-stage techniques such as Yolov5 and Gaussian Blurring were applied, SwinTransformer, Soft-Teacher, and Fast-RCNN techniques were applied to detect illegal crop objects, and SAHI open source framework was used as image slicing techniques. The illegal crop object detection model used an ensemble Soft-Teacher model using SwinTransformer as a Backbone network and Fast-RCNN as a detector. Experiments by applying image slicing techniques to this model showed that the mAP was 0.663, which is improved from 0.456, which is the mAP of the model without applying the conventional image slicing techniques.

KEYWORDS

object detection, image slicing, artificial intelligence, deep-learning, drone

Citation status

* References for papers published after 2023 are currently being built.

[other] Wang, Chien-Yao / 2022 / YOLOv7:Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors / arXiv preprint arXiv:2207.02696

[journal] Ahmed, Belal / 2020 / Image splicing detection using mask-RCNN / Signal, Image and Video Processing 14(5) : 1035~1042

[confproc] Zhu, Xingkui / 2021 / TPH-YOLOv5:Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios / Proceedings of the IEEE/CVF International Conference on Computer Vision

[confproc] Chen, Changrui / 2019 / Rrnet: A hybrid detector for object detection in drone-captured images / Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops

[confproc] Almahairi, Amjad / 2018 / Augmented cyclegan: Learning many-to-many mappings from unpaired data / International Conference on Machine Learning. PMLR

[confproc] Xu, Mengde / 2021 / End-to-end semi-supervised object detection with soft teacher / Proceedings of the IEEE/CVF International Conference on Computer Vision

[confproc] Liu, Ze / 2021 / Swin transformer:Hierarchical vision transformer using shifted windows / Proceedings of the IEEE/CVF International Conference on Computer Vision

[web] / https://www.cisp.or.kr/wp-content/uploads/2019/08/빅데이터_비식별화_기술_활용_안내서_ver_1.0.pdf / https://www.cisp.or.kr/wp-content/uploads/2019/08/빅데이터_비식별화_기술_활용_안내서_ver_1.0.pdf

[other] Akyon, Fatih / 2022 / Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection / arXiv preprint arXiv:2202.06934

[confproc] He, Kaiming / 2016 / Deep residual learning for image recognition / Proceedings of the IEEE conference on computer vision and pattern recognition

[confproc] KUANG, Zhenzhong / 2021 / Effective De-identification Generative Adversarial Network for Face Anonymization / Proceedings of the 29th ACM International Conference on Multimedia : 3182~3191

KJCKorea
Journal Central

Journal of Software Assessment and Valuation 2023 KCI Impact Factor : 0.35

Design and Implementation of an Illegal Crop Object Detection System using Image Slicing and Transformer Techniques to High-Resolution Drone Data

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of Software Assessment and Valuation 2023 KCI Impact Factor : 0.35

Design and Implementation of an Illegal Crop Object Detection System using Image Slicing and Transformer Techniques to High-Resolution Drone Data

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (11) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.