Filters








8,563 Hits in 6.2 sec

Deployment of Customized Deep Learning based Video Analytics On Surveillance Cameras [article]

Pratik Dubal, Rohan Mahadev, Suraj Kothawade, Kunal Dargan, Rishabh Iyer
2018 arXiv   pre-print
By sharing our implementation details and the experiences learned from deploying customized deep learning models for various customers, we hope that customized deep learning based video analytics is widely  ...  This paper demonstrates the effectiveness of our customized deep learning based video analytics system in various applications focused on security, safety, customer analytics and process compliance.  ...  Since, these off-the-shelf models are not customized for faces detected from surveillance cameras.  ... 
arXiv:1805.10604v2 fatcat:xzckmwvyv5hvfik35awnvwc2ji

Towards Multimodal Surveillance for Smart Building Security

Giuseppe Amato, Paolo Barsocchi, Fabrizio Falchi, Erina Ferro, Claudio Gennaro, Giuseppe Leone, Davide Moroni, Ovidio Salvetti, Claudio Vairo
2018 Proceedings (MDPI)  
On the other hand, by combining information coming from different sources, the overall performance of a surveillance system can be improved.  ...  The main goal of a surveillance system is to collect information in a sensing environment and notify unexpected behavior.  ...  donation of the Titan X Pascal GPU used in this research, and the "Renewed Energy" project of the DIITET Department of CNR for supporting the Smart Area activity, in whose framework this research is carried on  ... 
doi:10.3390/proceedings2020095 fatcat:mgczjxnqvbhunkavsa6jxsnf44

Deep learning-based vehicle occupancy detection in an open parking lot using thermal camera

Vijay Paidi, Hasan Fleyeh, Roger G. Nyberg
2020 IET Intelligent Transport Systems  
Multiple deep learning networks such as Yolo, Yolo-conv, GoogleNet, ReNet18 and ResNet50 with varying layers and architectures were evaluated on vehicle detection.  ...  Thermal camera was used to collect videos during varying environmental conditions and frames from these videos were extracted to prepare the dataset.  ...  A custom deep learning algorithm based on Yolo, depthwise and residual layers was developed to identify vehicles.  ... 
doi:10.1049/iet-its.2019.0468 fatcat:yuqwq7sbmrbhjcmkpsgoixvfhy

Towards Multimodal Surveillance For Smart Building Security

Giuseppe Amato, Paolo Barsocchi, Fabrizio Falchi, Erina Ferro, Claudio Gennaro, Giuseppe Leone, Davide Moroni, Ovidio Salvetti, Claudio Vairo
2018 Zenodo  
Search is based on the information extracted from the video streams during the analysis and the understanding phase.  ...  We also describe the different technologies, based on sensors and cameras, and the software solutions we implemented and that we aim to integrate in order to realize the surveillance scenario described  ... 
doi:10.5281/zenodo.1159161 fatcat:fzcws6auqrd75mqiok57jgctiu

The INUS Platform: A Modular Solution for Object Detection and Tracking from UAVs and Terrestrial Surveillance Assets

Evangelos Maltezos, Athanasios Douklias, Aris Dadoukis, Fay Misichroni, Lazaros Karagiannidis, Markos Antonopoulos, Katerina Voulgary, Eleftherios Ouzounoglou, Angelos Amditis
2021 Computation  
This paper proposes a multipurpose situational awareness platform by exploiting advanced on-board processing capabilities and efficient computer vision, image processing, and machine learning techniques  ...  Situational awareness is a critical aspect of the decision-making process in emergency response and civil protection and requires the availability of up-to-date information on the current situation.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/computation9020012 fatcat:ww2t7wgdrjeqrfa2zzqcrkk2ei

Deep-Framework: A Distributed, Scalable, and Edge-Oriented Framework for Real-Time Analysis of Video Streams

Alessandro Sassu, Jose Francisco Saenz-Cogollo, Maurizio Agelli
2021 Sensors  
In this work, we present Deep-Framework, a novel open source framework for developing edge-oriented real-time video analytics applications based on deep learning.  ...  Since most of the recent advances regarding the extraction of information from images and video rely on computation heavy deep learning algorithms, there is a growing need for solutions that allow the  ...  Its aim was to bring the deep learning based analytics to-wards the source of the video streams by parallelizing and filtering streams on the network nodes.  ... 
doi:10.3390/s21124045 fatcat:tvj7bsrjzjcddlsjiqqro6oosa

Tracking Vehicle Cruising in an Open Parking Lot Using Deep Learning and Kalman Filter

Vijay Paidi, Hasan Fleyeh, Johan Håkansson, Roger G. Nyberg, Alain Lambert
2021 Journal of Advanced Transportation  
The vehicle is detected using Yolov3, modified Yolo, and custom Yolo deep learning architectures.  ...  This problem is evident globally and the intensity of the problem varies based on the demand of parking spaces.  ...  Deep learning algorithms are well suited to identify objects of interest with varying heat signatures [11] .  ... 
doi:10.1155/2021/1812647 fatcat:6stlxqvhq5bszcsugazs6dwxci

Autonomous Marine Robot Based on AI Recognition for Permanent Surveillance in Marine Protected Areas

J. Carlos Molina-Molina, Marouane Salhaoui, Antonio Guerrero-González, Mounir Arioua
2021 Sensors  
In this context, we propose an autonomous surface vehicle (ASV) model system for the surveillance of marine areas by detecting and recognizing vessels through artificial intelligence (AI)-based image recognition  ...  The world's oceans are one of the most valuable sources of biodiversity and resources on the planet, although there are areas where the marine ecosystem is threatened by human activities.  ...  The study was a joint research project between Conflicts of Interest: The authors have no conflict of interest to declare.  ... 
doi:10.3390/s21082664 pmid:33920075 pmcid:PMC8070409 fatcat:unm6wf5nkzfhrfpgwxzvcdg3pm

People Tracking and Re-Identifying in Distributed Contexts: Extension Study of PoseTReID [article]

Ratha Siv, Matei Mancas, Bernard Gosselin, Dona Valy, Sokchenda Sreng
2022 arXiv   pre-print
By evaluating on our PoseTReID datasets, even though those deep learning re-identification methods are designed for only short-term re-identification across multiple cameras or videos, it is worth showing  ...  This pyppbox is available on GitHub https://github.com/rathaumons/pyppbox .  ...  Both are based on pre-trained models and Weight MS+D+C→M. The extracted features or areas of interest of both results are very similar.  ... 
arXiv:2205.10086v2 fatcat:cs62t2jaabh2vmtzo354v3rrxy

Intelligent Parking Management System (PMS) based on Video Analytics

Neeru Mago
2017 International Journal of Advanced Research in Computer Science and Software Engineering  
In this paper, various existing Parking Management System (PMS) are reviewed and compared and an intelligent PMS based on Video Analytics is proposed.  ...  For example, at one location in the camera image plane, one pixel movement away from that location may cause 100 pixels of movement away from its original corresponding location on the map.  ...  An object of interest is identified. Both background elimination and background registration techniques are used to identify dynamic objects.  ... 
doi:10.23956/ijarcsse/sv7i5/0254 fatcat:uupyazlppzckhlorpnhnzi5pye

Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAV [article]

Xiaoliang Wang, Peng Cheng, Xinchuan Liu, Benedict Uzochukwu
2019 arXiv   pre-print
As the data-driven technologies evolved, machine learning algorithm, especially the deep learning approach has been intensively utilized to solve different traditional computer vision research problems  ...  Modern Convolutional Neural Networks based object detectors could be divided into two major categories: one-stage object detector and two-stage object detector.  ...  All of the base ResNet models are pre-trained on ImageNet [48] . Convolutional Neural Network is implemented based on the deep learning framework MXNet [49] .  ... 
arXiv:1808.05756v2 fatcat:ojtu5ymmujduhabxwlpip3azgm

A Novel Deep Learning based Automated Academic Activities Recognition in Cyber-Physical Systems

Muhammad Wasim, Imran Ahmed, Jamil Ahmad, Mohammad Mehedi Hassan
2021 IEEE Access  
Hence, we need a time and memory-efficient customized deep learning model for academic activity recognition tasks.  ...  Video-based activity recognition mainly comprises videos or images that include different motions of human from the camera; on the other hand, sensor-based activity recognition concentrates on the motion  ... 
doi:10.1109/access.2021.3073890 fatcat:xhjox7yxuzemlox2724diz6fz4

Clothing identification via deep learning: forensic applications

Marianna Bedeli, Zeno Geradts, Erwin van Eijk
2018 Forensic Sciences Research  
Deep learning is used to train the computer to classify images based on clothing content.  ...  The method proposed in this article aims to identify people based on the visual information derived from their attire.  ...  Disclosure statement No potential conflict of interest was reported by the authors. Funding This work was supported by the Netherlands Forensic Institute.  ... 
doi:10.1080/20961790.2018.1526251 pmid:30483672 pmcid:PMC6201771 fatcat:gq6lywcup5gnlnvzm6f75ewa2q

Using Social Signals to Predict Shoplifting: A Transparent Approach to a Sensitive Activity Analysis Problem

Shane Reid, Sonya Coleman, Philip Vance, Dermot Kerr, Siobhan O'Neill
2021 Sensors  
Until recently, most state-of-the-art vision-based approaches to this problem have relied heavily on the use of black box deep learning models.  ...  An automated approach to detecting behaviours associated with shoplifting using surveillance footage could help reduce these losses.  ...  signals from surveillance cameras [16] .  ... 
doi:10.3390/s21206812 pmid:34696025 fatcat:jtuovvagqjc23jqsijhzfqdk7m

A STUDY ON APPLICATION OF MACHINE LEARNING AND COMPUTER VISION FOR RETAIL PROJECTS

Rima Borah, Rajarajeswari S
2017 Asian Journal of Pharmaceutical and Clinical Research  
The challenging task is to processimages from all these cameras and allow automation of tasks never before considered.  ...  In this paper, a study was made on applications of computer vision techniques in retail andcustomer strategic projects.  ...  Some examples to be considered -the webcam as a tracking device in place of the mouse, the surveillance cameras to identify bicycle thieves and alert security, the smartphone cameras to capture images  ... 
doi:10.22159/ajpcr.2017.v10s1.20522 fatcat:tjaetlf34bcvlmb2654ton7lmq
« Previous Showing results 1 — 15 out of 8,563 results