Multi-Grained Deep Feature Learning for Robust Pedestrian Detection

Lin, Chunze; Lu, Jiwen; Zhou, Jie

doi:10.1109/tcsvt.2018.2883558

Cited by 27 publications

(7 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Brazil et al [10] proposed a multi-task infusion framework for joint pedestrian detection and semantic segmentation at both proposal generation and classification stages. Lin et al [108], [109] designed a scale-aware attention module to make the detector better focus on the regions of pedestrians. Gajjar et al [54] and Yun et al [229] proposed to use the visual saliency task as a preprocessing step to better focus on the regions of a pedestrian.…”

Section: Pure Cnn Based Pedestrian Detection Methodsmentioning

confidence: 99%

From Handcrafted to Deep Features for Pedestrian Detection: A Survey

Cao

Pang

Xie

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Pedestrian detection is an important but challenging problem in computer vision, especially in human-centric tasks. Over the past decade, significant improvement has been witnessed with the help of handcrafted features and deep features. Here we present a comprehensive survey on recent advances in pedestrian detection. First, we provide a detailed review of single-spectral pedestrian detection that includes handcrafted features based methods and deep features based approaches. For handcrafted features based methods, we present an extensive review of approaches and find that handcrafted features with large freedom degrees in shape and space have better performance. In the case of deep features based approaches, we split them into pure CNN based methods and those employing both handcrafted and CNN based features. We give the statistical analysis and tendency of these methods, where feature enhanced, part-aware, and post-processing methods have attracted main attention. In addition to single-spectral pedestrian detection, we also review multi-spectral pedestrian detection, which provides more robust features for illumination variance. Furthermore, we introduce some related datasets and evaluation metrics, and compare some representative methods. We conclude this survey by emphasizing open problems that need to be addressed and highlighting various future directions. Researchers can track an up-to-date list at https://github.com/JialeCao001/PedSurvey.

show abstract

Section: Pure Cnn Based Pedestrian Detection Methodsmentioning

confidence: 99%

From Handcrafted to Deep Features for Pedestrian Detection: A Survey

Cao

Pang

Xie

et al. 2022

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…Human posture can be predicted from the bottomup, for example, Rangesh and Trivedi [221] proposed a pipeline structure that combines articulated human posture prediction, which used a particle filter with Gaussian Process Dynamics Model (GPDM) to track the joint posture of pedestrians reliably through image sequence, so as to reduce driving accidents of intelligent vehicles. Lin et al [222] designed a scale perception network jointly trained in a semi supervised way. They predicted pedestrians of a specific scale by matching the perception field of pedestrians with the target scale and using the most appropriate feature maps, which could ensure a large tradeoff between accuracy and speed.…”

Section: Bottom-up Human Posture Predictionmentioning

confidence: 99%

A Survey of Human Action Recognition and Posture Prediction

Cheung

et al. 2022

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

Human action recognition and posture prediction aim to recognize and predict respectively the action and postures of persons in videos. They are both active research topics in computer vision community, which have attracted considerable attention from academia and industry. They are also the precondition for intelligent interaction and human-computer cooperation, and they help the machine perceive the external environment. In the past decade, tremendous progress has been made in the field, especially after the emergence of deep learning technologies.Hence, it is necessary to make a comprehensive review of recent developments. In this paper, firstly, we attempt to present the background, and then discuss research progresses. Secondly, we introduce datasets, various typical feature representation methods, and explore advanced human action recognition and posture prediction algorithms.Finally, facing the challenges in the field, this paper puts forward the research focus, and introduces the importance of action recognition and posture prediction by taking interactive cognition in self-driving vehicle as an example.

show abstract

“…Generally, the modern segmentation methods can be considered either proposal-based methods [ 13 ] or mask-based methods [ 14 ]. Proposal-based methods comprise a two-phase detection, and each region produces a proposal which is later segmented as a mask.…”

Section: Introductionmentioning

confidence: 99%

Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians

Alavianmehr

Helfroush

Danyali

et al. 2023

J Real-Time Image Proc

View full text Add to dashboard Cite

The detection of multi-scale pedestrians is one of the challenging tasks in pedestrian detection applications. Moreover, the task of small-scale pedestrian detection, i.e., accurate localization of pedestrians as low-scale target objects, can help solve the issue of occluded pedestrian detection as well. In this paper, we present a fully convolutional neural network with a new architecture and an innovative, fully detailed supervision for semantic segmentation of pedestrians. The proposed network has been named butterfly network (BF-Net) because of its architecture analogous to a butterfly. The proposed BF-Net preserves the ability of simplicity so that it can process static images with a real-time image processing rate. The sub-path blocks embedded in the architecture of the proposed BF-Net provides a higher accuracy for detecting multi-scale objective targets including the small ones. The other advantage of the proposed architecture is replacing common batch normalization with conditional one. In conclusion, the experimental results of the proposed method demonstrate that the proposed network outperform the other state-of-the-art networks such as U-Net + + , U-Net3 + , Mask-RCNN, and Deeplabv3 + for the semantic segmentation of the pedestrians.

show abstract

Multi-Grained Deep Feature Learning for Robust Pedestrian Detection

Cited by 27 publications

References 61 publications

From Handcrafted to Deep Features for Pedestrian Detection: A Survey

From Handcrafted to Deep Features for Pedestrian Detection: A Survey

A Survey of Human Action Recognition and Posture Prediction

Butterfly network: a convolutional neural network with a new architecture for multi-scale semantic segmentation of pedestrians

Contact Info

Product

Resources

About