Real time FPGA-ANN architecture for outdoor obstacle detection focused in road safety

Issue title: Special Section: Intelligent, Smart and Scalable Cyber-Physical Systems

Guest editors: V. Vijayakumar, V. Subramaniyaswamy, Jemal Abawajy and Longzhi Yang

Article type: Research Article

Authors: Algredo-Badillo, Ignacio^a | Morales-Rosales, Luis Alberto^{b; *} | Hernandez-Gracidas, Carlos Arturo^c | Cruz-Victoria, Juan Crescenciano^d | Pacheco-Bautista, Daniel^e | Morales-Sandoval, Miguel^f

Affiliations: [a] Conacyt-Instituto Nacional de Astrofisica, Optica y Electronica, Luis Enrique Erro #1, Santa Maria Tonatzintla, Puebla, Mexico | [b] Conacyt-Universidad Michoacana de San Nicolas de Hidalgo, Gral. Francisco J. Mugica S/N, Ciudad Universitaria, Morelia, Michoacan, Mexico | [c] Conacyt-Benemerita Universidad Autonoma de Puebla, 4 Sur #104; Col. Centro, Puebla de Zaragoza, Mexico | [d] Universidad Politecnica de Tlaxcala, Avenida Universidad Politecnica No.1, San Pedro Xalcaltinco, Tlaxcala, Mexico | [e] Universidad del Istmo, Ciudad Universitaria S/N, Santa Cruz, Tehuantepec, Oaxaca, Mexico | [f] CINVESTAV, Carretera Victoria- Soto la Marina Kilometro 5.5, Ciudad Victoria - Soto la Marina, 87130 Cd Victoria, Tamps

Correspondence: [*] Corresponding author. Morales-Rosales Luis Alberto, Conacyt-Universidad Michoacana de San Nicolas de Hidalgo, Gral. Francisco J. Mugica S/N, Ciudad Universitaria, Morelia, Michoacan, Mexico. E-mail: lamorales@conacyt.mx.

Abstract:  Object detection is a technologically challenging issue, which is useful for safety in outdoor environments, where this object, frequently, represents an obstacle that must be avoided. Although several object detection methods have been developed in recent years, they usually tend to produce poor results in outdoor environments, being mainly affected by sunlight, light intensity, shadows, and limited computational resources. This open problem is the main motivation for exploring the challenge of developing low-cost object detection solutions, with the characteristic of being easily adaptable and having low power requirements, such as the ones needed in on-board obstacle detection systems in automobiles. In this work, we present a trade-off analysis of several architectures using an FPGA-based design that implements ANNs (FPGA-ANN) for outdoor obstacle detection, focused in road safety. The analyzed FPGA-ANN architectures merge outdoor data gathered by a Kinect sensor, images and infrared data, to construct an outdoor environment model for object detection, which allows to detect if there is an obstacle in the near surroundings of a vehicle.

Keywords: Obstacle detection, artificial neural networks, FPGA implementation, architecture trade-off analysis, road safety

DOI: 10.3233/JIFS-169997

Journal: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 5, pp. 4425-4436, 2019