TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios

计算机科学 人工智能 可解释性 无人机 分类器(UML) 对象(语法) 目标检测 机器学习 变压器 模式识别(心理学) 工程类 遗传学 生物 电气工程 电压
作者
Xingkui Zhu,Shuchang Lyu,Xu Wang,Qi Zhao
出处
期刊:International Conference on Computer Vision 卷期号:: 2778-2788 被引量:2190
标识
DOI:10.1109/iccvw54120.2021.00312
摘要

Object detection on drone-captured scenarios is a recent popular task. As drones always navigate in different altitudes, the object scale varies violently, which burdens the optimization of networks. Moreover, high-speed and low-altitude flight bring in the motion blur on the densely packed objects, which leads to great challenge of object distinction. To solve the two issues mentioned above, we propose TPH-YOLOv5. Based on YOLOv5, we add one more prediction head to detect different-scale objects. Then we replace the original prediction heads with Transformer Prediction Heads (TPH) to explore the prediction potential with self-attention mechanism. We also integrate convolutional block attention model (CBAM) to find attention region on scenarios with dense objects. To achieve more improvement of our proposed TPH-YOLOv5, we provide bags of useful strategies such as data augmentation, multi-scale testing, multi-model integration and utilizing extra classifier. Extensive experiments on dataset VisDrone2021 show that TPH-YOLOv5 have good performance with impressive interpretability on drone-captured scenarios. On DET-test-challenge dataset, the AP result of TPH-YOLOv5 are 39.18%, which is better than previous SOTA method (DPNetV3) by 1.81%. On VisDrone Challenge 2021, TPH-YOLOv5 wins 5thplace and achieves well-matched results with 1stplace model (AP 39.43%). Compared to baseline model (YOLOv5), TPH-YOLOv5 improves about 7%, which is encouraging and competitive.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
tingt完成签到,获得积分10
刚刚
夏夏夏发布了新的文献求助10
刚刚
dianhuaxue发布了新的文献求助10
刚刚
刚刚
1秒前
Ian发布了新的文献求助10
1秒前
Akim的应助被fx采纳,获得10
1秒前
风趣乐天发布了新的文献求助10
1秒前
1秒前
Lisa的应助被fx采纳,获得10
1秒前
zkylh的应助被fx采纳,获得10
1秒前
Lucas的应助被fx采纳,获得10
2秒前
香蕉觅云的应助被zzk采纳,获得10
2秒前
fwfl250发布了新的文献求助10
2秒前
蜡笔小新完成签到 ,获得积分10
3秒前
猴子的应助被明亮白山采纳,获得10
3秒前
3秒前
领导范儿的应助被傻傻的灵寒采纳,获得10
4秒前
4秒前
4秒前
4秒前
HHW发布了新的文献求助10
5秒前
wanci的应助被牧百川采纳,获得10
5秒前
良行知发布了新的文献求助10
5秒前
5秒前
英姑的应助被jackson_WANG采纳,获得10
6秒前
tldsnhzrs完成签到,获得积分10
6秒前
小梅同学完成签到,获得积分10
7秒前
277发布了新的文献求助10
7秒前
8秒前
Jasper的应助被Ian采纳,获得150
8秒前
虚心楼房发布了新的文献求助10
8秒前
马秀玲发布了新的文献求助10
8秒前
8秒前
QIU完成签到 ,获得积分10
8秒前
9秒前
酷波er的应助被良行知采纳,获得10
12秒前
13秒前
酒辞发布了新的文献求助10
13秒前
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183298
求助须知:如何正确求助?哪些是违规求助? 9572606
关于积分的说明 21826444
捐赠科研通 7780272
什么是DOI,文献DOI怎么找? 3433993
关于科研通互助平台的介绍 2558136
邀请新用户注册赠送积分活动 2480259