L4Net: An anchor‐free generic object detector with attention mechanism for autonomous driving

Generic Object Detection for Autonomous Robots

Artificial Intelligence for Autonomous robots is a growing line of interest for researchers. Computer Vision techniques for Object Detection and Recognition are widely applied in this domain to increase to robots interaction. In this paper, we present a generic Object Detection System for autonomous robots simulated in the Aibo robot of Sony. The detection process is done by means of cascades o...

Joint Attention in Autonomous Driving (JAAD)

In this paper we present a novel dataset for a critical aspect of autonomous driving, the joint attention that must occur between drivers and of pedestrians, cyclists or other drivers. This dataset is produced with the intention of demonstrating the behavioral variability of traffic participants. We also show how visual complexity of the behaviors and scene understanding is affected by various ...

An Object-Oriented Abstraction Mechanism for Generic Enterprise Modeling

A generic object-oriented enterprise modeling process (GOOEMP) is a set of partially ordered steps intended to reach the objective of building a fully integrated, dynamic, object-oriented model of the enterprise. An abstraction mechanism is proposed to enable this process. The process is generic because it applies to most types of enterprises. Enterprise models are the products developed from t...

Driving an autonomous car with eye tracking

This paper describes eyeDriver, a hardware and software setup to drive an autonomous car with eye movement. The movement of the operator’s iris is tracked with an infrared sensitive camera built onto a HED4 interface by SMI. The position of the iris is then propagated by eyeDriver to control the steering wheel of “Spirit of Berlin”, a completely autonomous car developed by the Free University o...

Object Detection for Autonomous Driving Using Deep Learning