Deep Learning based on CNN for Pedestrian Detection: An Overview and Analysis

Saeidi, Mahmoud; Ahmadi, Ali

doi:10.1109/istel.2018.8661043

Cited by 9 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is also necessary to adopt strategies to improve the performance of algorithms and methods used to classify data and semantic information in occlusion conditions. Saeidi and Ahmadi [28] first examined some of the DCNN-based learning methods and briefly explained the new algorithms proposed by various researchers for these methods. Next, the researchers proposed a deep architectural method and a new training method based on parallel DCNNs for pedestrian detection.…”

Section: Proposed Methods For Pedestrian Detectionmentioning

confidence: 99%

Applications of Deep Learning Techniques for Pedestrian Detection in Smart Environments: A Comprehensive Study

Olia

Oskouei

et al. 2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

Intelligent transportation systems have been very well received by car companies, people, and governments around the world. The main challenge in the world of smart and self-driving cars is to identify obstacles, especially pedestrians, and take action to prevent collisions with them. Many studies in this field have been done by various researchers, but there are still many errors in the accurate detection of pedestrians in self-made cars made by different car companies, so in the research in this study, we focused on the use of deep learning techniques to identify pedestrians for the development of intelligent transportation systems and self-driving cars and pedestrian identification in smart cities, and then some of the most common deep learning techniques used by various researchers were reviewed. Finally, in this research, the challenges in each field are discovered, which can be very useful for students who are looking for an idea to do their dissertations and research in the field of smart transportation and smart cities.

show abstract

Section: Proposed Methods For Pedestrian Detectionmentioning

confidence: 99%

Applications of Deep Learning Techniques for Pedestrian Detection in Smart Environments: A Comprehensive Study

Olia

Oskouei

et al. 2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…Some algorithms use shallow classifiers such as SVM [39][40][41] or Boosting [42][43][44]. Others integrate a framework that performs the classifying and extracting functions [25,45,46]. These algorithms add a regression method that runs together with the classification function to improve the location quality of the bounding boxes [47][48][49].…”

Section: Related Workmentioning

confidence: 99%

Integration of Wearables and Wireless Technologies to Improve the Interaction between Disabled Vulnerable Road Users and Self-Driving Cars

Guerrero-Ibañez,

Amezcua-Valdovinos,

Contreras-Castillo

2023

Electronics

View full text Add to dashboard Cite

The auto industry is accelerating, and self-driving cars are becoming a reality. However, the acceptance of such cars will depend on their social and environmental integration into a road traffic ecosystem comprising vehicles, motorcycles, bicycles, and pedestrians. One of the most vulnerable groups within the road ecosystem is pedestrians. Assistive technology focuses on ensuring functional independence for people with disabilities. However, little effort has been devoted to exploring possible interaction mechanisms between pedestrians with disabilities and self-driving cars. This paper analyzes how self-driving cars and disabled pedestrians should interact in a traffic ecosystem supported by wearable devices for pedestrians to feel safer and more comfortable. We define the concept of an Assistive Self-driving Car (ASC). We describe a set of procedures to identify people with disabilities using an IEEE 802.11p-based device and a group of messages to express the intentions of disabled pedestrians to self-driving cars. This interaction provides disabled pedestrians with increased safety and confidence in performing tasks such as crossing the street. Finally, we discuss strategies for alerting disabled pedestrians to potential hazards within the road ecosystem.

show abstract

“…Classificadores de dois estágios utilizam a RPN, assim, no primeiro estágio ocorre a gerac ¸ão de objetos candidatos via caixas delimitadoras bounding boxes. A RPN é uma rede totalmente convolucional que prediz as coordenadas do objeto na imagem, bem como, o nível de detecc ¸ão [22]. O segundo estágio extrai as características destes usando RoI-Pool, e executa a classificac ¸ão e regressão das bounding boxes [19].…”

Section: A Referencial Teóricounclassified

Um Estudo Comparativo de Redes Convolucionais Profundas para Detecção de Insetos em Imagens

Domênico

Lau²,

Ribeiro³

et al. 2021

Anais Estendidos Da XXXIV Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2021)

View full text Add to dashboard Cite

Esse trabalho apresenta um estudo comparativo entre dois modelos de redes convolucionais profundas em tarefas de identificação e contagem de insetos em imagens digitais, considerando afídeos (Hemiptera: Aphididae) e parasitoides (Hymenoptera: Aphelinidae e Braconidae, Aphidiinae). Nesse estudo de caso, cada imagem pode conter centenas de espécimes, detritos, sobreposições e outros insetos com morfologia semelhante, o que dificulta o processo de detecção. Nesse sentido, comparou-se os resultados obtidos pelo sistema InsectCV, baseado em Mask RCNN, em termos de tempo de treinamento, inferência e precisão, com um novo modelo, treinado com a rede DarkNet. Com a utilização de imagens em tons de cinza, com menor dimensão, processamento via GPU e uma rede convolucional de um estágio, é possível a redução do custo computacional e elevação da precisão na tarefa de detecção de objetos. Com base em 580 imagens utilizadas para a validação do modelo proposto foi possível obter a precisão média de 79,9%.

show abstract

Deep Learning based on CNN for Pedestrian Detection: An Overview and Analysis

Cited by 9 publications

References 26 publications

Applications of Deep Learning Techniques for Pedestrian Detection in Smart Environments: A Comprehensive Study

Applications of Deep Learning Techniques for Pedestrian Detection in Smart Environments: A Comprehensive Study

Integration of Wearables and Wireless Technologies to Improve the Interaction between Disabled Vulnerable Road Users and Self-Driving Cars

Um Estudo Comparativo de Redes Convolucionais Profundas para Detecção de Insetos em Imagens

Contact Info

Product

Resources

About