Last decade has seen an exponential growth of the presence of computer vision systems in many sectors due to the explosion in consumer electronics, consolidation of the information society, the reduced costs of hardware production, and the significant contributions of scientific communities in the development of algorithms and methods.
Most noteworthy, in the field of Intelligent Transport Systems and intelligent vehicles, the technology has favoured the appearance of a number of systems to improve comfort, safety and efficiency of transport. Examples of these systems are GPS navigation systems, automatic cruise control, vehicle identification, communication and eCall, and more recently advanced driver assistance systems like lane departure warning, driver drowsiness detection, or semiautomated driving systems like platooning, parking assistance, etc.
The abovementioned systems cover a wide range of services for the driver that make intensive use of sensing systems, that allow obtaining data from the environment of the vehicle to understand the situations and take actions (e.g. send the information to the driver, actuate on the vehicle, launch communication channels, etc). The introduction of such systems to the market is strongly conditioned to reaching cost-effective solutions, which is not an easy task since sensing systems typically are based on expensive technologies, or difficult to miniaturize.
Computer vision systems have broken through this market for several reasons: (i) richness of the information contained in images; (ii) advances in electronics and optics that allow reducing the size and cost of cameras; (iii) the growing computational capacity of embedded systems; and (iv) the outstanding contributions of scientific communities in image processing, projective geometry and machine learning (to mention a few). This last point is crucial because it opens the door to the definition of uncountable innovative methods and the creation of new services.
From research to market
During the last three decades there has been numerous research programs aiming to give steps towards the introduction of intelligent systems into vehicles, like the DARPA Grand and Urban Challenge, EUREKA Prometheus, or Google driverless car just to mention a few. These programs exemplify the effort of the scientific community, which has proposed since a vast number of algorithms, methods and technologies for intelligent vehicles. The target of these programs was to learn, test and evolve the technology in an exercise of exploring the possibilities that technology can offer to drivers in particular and the transport sector in general.
For the tests, intelligent prototype vehicles have been used, equipped with prototype sensors, large size radar, laser, GPS, antennas, multiple cameras, CPUs, batteries, etc. These cars demonstrate only the feasibility of the technical part of deploying intelligent vehicles. There is a very steep path from these vehicles to solutions for the market, considering also legal aspects, space, cost and consumption constraints of HW.
Historically, only the more basic ADAS (night vision, lane departure warning, safety distance warning) have reached the market, and only to high-end vehicles, as the result of working hard in the reduction of the complexity of algorithms, and their optimization into low capacity, low cost embedded platforms.
These days, ADAS systems in midrange vehicles are closer, thanks to the advances in more efficient computer vision methods, more easy-to-program and reduced cost embedded HW, and the growing interest of large manufacturers that compete for the market.
Among this wide range of aspects that make this technological success possible, in this paper we wanted to focus on the aspects of the design of computer vision methods, describing our own methods as example of how to find a trade-off between real-time and functionality.