François Marmoiton

Outdoor autonomous navigation using monocular vision

In this paper, a complete system for outdoor robot navigation is presented. It uses only monocular vision. The robot is first guided on a path by a human. During this learning step, the robot records a video sequence. From this sequence, a three dimensional map of the trajectory and the environment is built. When this map has been computed, the robot is able to follow the same trajectory by itself. Experimental results carried out with an urban electric vehicle are shown and compared to the ground truth.

Hardware, Design and Implementation Issues on a Fpga-Based Smart Camera

Processing images to extract useful information in real-time is a complex task, dealing with large amounts of iconic data and requiring intensive computation. Smart cameras use embedded processing to save the host system from the low-level processing load and to reduce communication flows and overheads. Field programmable devices present special interest for smart cameras design: flexibility, reconfigurability and parallel processing skills are some specially important features. In this paper we present a FPGA-based smart camera research platform. The hardware architecture is described, and some design issues are discussed. Our goal is to use the possibility to reconfigure the FPGA device in order to adapt the system architecture to a given application. To that, a design methodology, based on pre-programmed processing elements, is proposed and sketched. Some implementation issues are discussed and a template tracking application is given as example, with its experimental results.

Nonlinear Control for Urban Vehicles Platooning, Relying upon a Unique Kinematic GPS

In order to solve problems of traffic saturation in cities, new alternative” Urban Transportation Systems” are based on electric vehicles in free-access. One necessary functionality of such systems is their ability to move in a platoon fashion. Platooning of these automatic guided vehicles, relying on RTK-GPS sensors and inter-vehicles communication, is addressed in this paper. More precisely, vehicles platoon is expected to follow a curved reference path. Relying on nonlinear control theory, lateral and longitudinal control are fully decoupled, and therefore addressed independently. To ensure passengers comfort, additional monitoring functions supervise our control system. Then, simulations followed by experiments carried out with urban vehicles, are presented.

Accurate automatic guidance of an urban electric vehicle relying on a kinematic GPS sensor

Abstract Automatic guidance of urban electric vehicles is addressed in this paper. It is shown that nonlinear control design (namely chained form conversion) and the use of a RTK GPS sensor allow to achieve curved path following with a very high accuracy. Extensive experiments, carried out with a Cycab vehicle, are discussed.

Road detection and vehicles tracking by vision for an on-board ACC system in the VELAC vehicle

The paper presents a method designed to detect and track vehicles on highway in a safety improvement purpose. The goal of this kind of system is to regulate the speed of a vehicle so as to respect safety distances relative to vehicles ahead. The method is exclusively based on monocular computer vision and uses two algorithms. The first one is able to locate the lane borders in the image, and to deduce the 3D shape of the road axis. The second algorithm detects, tracks and computes the 3D location of vehicles ahead by using fixed lights embedded on these vehicles. By combining the results of the two algorithms, a fusion step permits us to know were the most dangerous vehicle is, according to its position, speed and circulation lane. The method has been implemented on our experimental vehicle VELAC and the whole system operates in real time conditions.

Road Detection and Vehicle Tracking by Vision for Adaptive Cruise Control

This article deals first with a process designed to detect the circulation lane of a vehicle by onboard monocular vision. This detection process is based on a recursive updating of a statistical model of the lane obtained by a training phase. Once the lane has been located, a reconstruction algorithm computes the vehicle location on its lane and the three-dimensional shape of the road. Thereafter, the authors seek to detect and track vehicles situated in front of their vehicle and equipped with specific visual markers in order to achieve an accurate determination of their location and speed. By combining these various data, the most dangerous obstacle can be identified. Each of these three processes is described in detail, and significant examples are provided.

Transform image coding with global thresholding: application to baseline JPEG

Many image compression schemes perform the discrete cosine transform (DCT) to represent an image in frequency space. An analysis of a suite of images confirms that the luminance AC coefficients can be modeled by a Laplacian distribution. The distribution model can be used to drop the insignificant coefficients. In this paper we develop an image-adaptive JPEG encoding algorithm that incorporates global thresholding and near optimal quantization approach based on Lagrangian multiplier. Simulation results demonstrate that, with our thresholding technique, we can improve the reconstructed image quality compared to the one provided by other DCT image coding schemes without thresholding.

Towards an Embedded Visuo-Inertial Smart Sensor

In the neurological system of primates, changes in posture are detected by the central nervous system through a vestibular process. This process, located in the inner ear, coordinates several system outputs to maintain stable balance, visual gaze, and autonomic control in response to changes in posture. Consequently the vestibular data is merged to other sensing data like touch, vision, .... The visuo-inertial merging is crucial for several tasks like navigation, depth estimation, stabilization. This paper proposes a “primate-inspired” sensing hardware, based on a CMOS imaging and an artificial vestibular system. The whole sensor can be considered like a smart embedded sensor where one of the most original aspects of this approach is the use of a System On Chip implemented in a FPGA to manage the whole system. The sensing device is designed around a 4 million pixels CMOS imager and the artificial vestibular set is composed of three linear accelerometers and three gyroscopes. With its structure, the system provides a high degree of versatility and allows the implementation of parallel image and inertial processing algorithms. In order to illustrate the proposed approach, depth estimation with Kalman filtering implementation is carried out.

Location and relative speed estimation of vehicles by monocular vision

We consider the problems of perception of an adaptive cruise control system. The purpose of this type of system is to regulate the speed of our vehicle so as to respect safety distances relative to vehicles ahead. The work described concerns the detection, location and especially tracking, by monocular vision, of target vehicles equipped with virtual marks. We focus on precise determination of the position and relative speed of the target vehicles. We show an example of cooperation between road detection and obstacle detection. The methods presented are tested on real roads on our VELAC demonstration vehicle. We include results obtained by this means.

Wavelet image coding with parametric thresholding: application to JPEG2000

With the increasing use of multimedia technologies, image compression requires higher performance as well as new features. To address this need in the specific area of image coding, the latest ISO/IEC image compression standard, JPEG2000, has been developed. In part II of the standard, the Wavelet Trellis Coded Quantization (WTCQ) algorithm was adopted. It has been proved that this quantization design provides subjective image quality superior to other existing quantization techniques. In this paper we are aiming to improve the rate-distortion performance of WTCQ, by incorporating a thresholding process in JPEG2000 coding chain. The threshold decisions are derived in a Bayesian framework, and the prior used on the wavelet coefficients is the generalized Gaussian distribution (GGD). The threshold value depends on the parametric model estimation of the subband wavelet coefficient distribution. Our algorithm approaches the lowest possible memory usage by using line-based wavelet transform and a scan-based bit allocation technique. In our work, we investigate an efficient way to apply the TCQ to wavelet image coding with regard to both the computational complexity and the compression performance. Experimental results show that the proposed algorithm performs competitively with the best available coding algorithms reported in the literature in terms quality performance.