Detecting 32 Pedestrian Attributes for Autonomous Vehicles

行人 计算机科学 规范化(社会学) 人工智能 领域(数学) 背景(考古学) 高级驾驶员辅助系统 机器学习 运输工程 工程类 地理 人类学 数学 社会学 考古 纯数学
作者
Taylor Mordan,Matthieu Cord,Patrick Pérez,Alexandre Alahi
出处
期刊:IEEE Transactions on Intelligent Transportation Systems [Institute of Electrical and Electronics Engineers]
卷期号:23 (8): 11823-11835 被引量:25
标识
DOI:10.1109/tits.2021.3107587
摘要

Pedestrians are arguably one of the most safety-critical road users to consider for autonomous vehicles in urban areas. In this paper, we address the problem of jointly detecting pedestrians and recognizing 32 pedestrian attributes from a single image. These encompass visual appearance and behavior, and also include the forecasting of road crossing, which is a main safety concern. For this, we introduce a Multi-Task Learning (MTL) model relying on a composite field framework, which achieves both goals in an efficient way. Each field spatially locates pedestrian instances and aggregates attribute predictions over them. This formulation naturally leverages spatial context, making it well suited to low resolution scenarios such as autonomous driving. By increasing the number of attributes jointly learned, we highlight an issue related to the scales of gradients, which arises in MTL with numerous tasks. We solve it by normalizing the gradients coming from different objective functions when they join at the fork in the network architecture during the backward pass, referred to as fork-normalization. Experimental validation is performed on JAAD, a dataset providing numerous attributes for pedestrian analysis from autonomous vehicles, and shows competitive detection and attribute recognition results, as well as a more stable MTL training.
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
1秒前
2秒前
kmssh完成签到,获得积分10
2秒前
NexusExplorer应助耍酷芷珍采纳,获得10
2秒前
自信的蓝天完成签到 ,获得积分10
3秒前
3秒前
111发布了新的文献求助10
4秒前
桐桐应助VDC采纳,获得10
4秒前
佳丽发布了新的文献求助10
5秒前
6秒前
善学以致用应助Coarrb采纳,获得10
7秒前
7秒前
猪猪想要平静的生活完成签到,获得积分10
7秒前
7秒前
哈比人linling完成签到,获得积分10
9秒前
怡然诗霜完成签到,获得积分10
9秒前
找回自己完成签到,获得积分10
10秒前
你是我的小月亮完成签到 ,获得积分10
11秒前
小苏打发布了新的文献求助10
11秒前
喁喁哥完成签到,获得积分10
12秒前
ding应助柚子采纳,获得150
13秒前
13秒前
斯文败类应助111采纳,获得10
13秒前
14秒前
科研民工_郭完成签到,获得积分10
14秒前
14秒前
min完成签到,获得积分10
14秒前
gyl完成签到 ,获得积分10
15秒前
15秒前
小二郎应助保护番茄采纳,获得10
16秒前
劲秉应助佳丽采纳,获得20
17秒前
min发布了新的文献求助10
18秒前
18秒前
田様应助SYH采纳,获得10
18秒前
re6irth完成签到,获得积分10
18秒前
20秒前
20秒前
仁爱的雁芙完成签到,获得积分10
20秒前
21秒前
Lucas应助964230130采纳,获得30
22秒前
高分求助中
All the Birds of the World 4000
Production Logging: Theoretical and Interpretive Elements 3000
Les Mantodea de Guyane Insecta, Polyneoptera 2000
Am Rande der Geschichte : mein Leben in China / Ruth Weiss 1500
CENTRAL BOOKS: A BRIEF HISTORY 1939 TO 1999 by Dave Cope 1000
Machine Learning Methods in Geoscience 1000
Resilience of a Nation: A History of the Military in Rwanda 888
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3738035
求助须知:如何正确求助?哪些是违规求助? 3281550
关于积分的说明 10025988
捐赠科研通 2998302
什么是DOI,文献DOI怎么找? 1645228
邀请新用户注册赠送积分活动 782660
科研通“疑难数据库(出版商)”最低求助积分说明 749882