Published on Mon Jul 27 2020

YOLOpeds: Efficient Real-Time Single-Shot Pedestrian Detection for Smart Camera Applications

Christos Kyrkou

Deep Learning-based object detectors can enhance the capabilities of smart cameras. They can be used for video surveillance, autonomous driving, robots and drones, smart factory, and health monitoring. Efficient neural networks can also be a key enabler of privacy and security.

0
0
0
Abstract

Deep Learning-based object detectors can enhance the capabilities of smart camera systems in a wide spectrum of machine vision applications including video surveillance, autonomous driving, robots and drones, smart factory, and health monitoring. Pedestrian detection plays a key role in all these applications and deep learning can be used to construct accurate state-of-the-art detectors. However, such complex paradigms do not scale easily and are not traditionally implemented in resource-constrained smart cameras for on-device processing which offers significant advantages in situations when real-time monitoring and robustness are vital. Efficient neural networks can not only enable mobile applications and on-device experiences but can also be a key enabler of privacy and security allowing a user to gain the benefits of neural networks without needing to send their data to the server to be evaluated. This work addresses the challenge of achieving a good trade-off between accuracy and speed for efficient deployment of deep-learning-based pedestrian detection in smart camera applications. A computationally efficient architecture is introduced based on separable convolutions and proposes integrating dense connections across layers and multi-scale feature fusion to improve representational capacity while decreasing the number of parameters and operations. In particular, the contributions of this work are the following: 1) An efficient backbone combining multi-scale feature operations, 2) a more elaborate loss function for improved localization, 3) an anchor-less approach for detection, The proposed approach called YOLOpeds is evaluated using the PETS2009 surveillance dataset on 320x320 images. Overall, YOLOpeds provides real-time sustained operation of over 30 frames per second with detection rates in the range of 86% outperforming existing deep learning models.

Fri Dec 28 2018
Computer Vision
CamLoc: Pedestrian Location Detection from Pose Estimation on Resource-constrained Smart-cameras
Video processing holds utility for many emerging applications and data labeling in the IoT space. However, performing this video processing with deep neurological networks at the edge of the Internet is not trivial. We demonstrate that CamLoc is an efficient solution for location estimation in videos on smart-cameras.
0
0
0
Sat Dec 21 2019
Computer Vision
Seek and You Will Find: A New Optimized Framework for Efficient Detection of Pedestrian
Study of object detection and localization, particularly pedestrian detection have received considerable attention in recent times. A significant trend of latest research studies is the use of sophisticated Deep Learning based approaches to improve benchmark performance on various standard datasets.
0
0
0
Wed Feb 15 2017
Computer Vision
Deep Multi-camera People Detection
This paper addresses the problem of multi-view people occupancy map. Existing solutions for this problem either operate per-view, or rely on background subtraction pre-processing. Our end-to-end deep learning method outperforms existing methods by large margins.
0
0
0
Fri Sep 01 2017
Computer Vision
Too Far to See? Not Really! --- Pedestrian Detection with Scale-aware Localization Policy
A major bottleneck of pedestrian detection lies on the sharp performance of small-size pedestrians that are relatively far from the camera. Motivated by the observation that pedestrians of disparateatial scales exhibit distinct visual appearances, we propose an active pedestrian detector that explicitly operates over multiple-layer neurons.
0
0
0
Tue Oct 13 2015
Computer Vision
Deep convolutional neural networks for pedestrian detection
Pedestrian detection is a popular research topic due to its paramountipientimportance for a number of applications, especially in the fields of automotive, surveillance and robotics. In this paper, we propose a pedestrian detection system based on deep learning, adapting a general-purpose convolutional
0
0
0
Sat Jun 05 2021
Computer Vision
Multi-Camera Vehicle Counting Using Edge-AI
This paper presents a novel solution to automatically count vehicles in a parking lot using images captured by smart cameras. Unlike most of the literature on this task, which focuses on the analysis of single images, this paper proposes the use of multiple visual sources to monitor a wider parking area.
2
0
0