Real-time multiple vehicle detection and tracking from a moving vehicle

Abstract. A real-time vision system has been developed that analyzes color videos taken from a forward-looking video camera in a car driving on a highway. The system uses a combination of color, edge, and motion information to recognize and track the road boundaries, lane markings and other vehicles on the road. Cars are recognized by matching templates that are cropped from the input data online and by detecting highway scene features and evaluating how they relate to each other. Cars are also detected by temporal differencing and by tracking motion parameters that are typical for cars. The system recognizes and tracks road boundaries and lane markings using a recursive least-squares filter. Experimental results demonstrate robust, real-time car detection and tracking over thousands of image frames. The data includes video taken under difficult visibility conditions. Received: 1 September 1998 / Accepted: 22 February 2000     

A model-driven approach for real-time road recognition

This article describes a method designed to detect and track road edges starting from images provided by an on-board monocular monochromic camera. Its implementation on specific hardware is also presented in the framework of the VELAC project. The method is based on four modules: (1) detection of the road edges in the image by a model-driven algorithm, which uses a statistical model of the lane sides which manages the occlusions or imperfections of the road marking – this model is initialized by an off-line training step; (2) localization of the vehicle in the lane in which it is travelling; (3) tracking to define a new search space of road edges for the next image; and (4) management of the lane numbers to determine the lane in which the vehicle is travelling. The algorithm is implemented in order to validate the method in a real-time context. Results obtained on marked and unmarked road images show the robustness and precision of the method. Received: 18 November 2000 / Accepted: 7 May 2001     

Visual routines for real-time monitoring of vehicle behavior

Low-cost, purely visual modules are presented, which are able to reliably perform real-time computation of kinematic quantities relevant for the navigation of commercial vehicles moving along highways or motorways. Taking as input a video stream of b/w images coming from a standard camera mounted aboard the vehicle, the modules return instantaneous measurements for the speed of the vehicle, its lateral position in the lane, and the distance from the preceding vehicle. The modules, which are designed to work in real-time on standard PC platforms, have been tested under typical working conditions. Preliminary results are reported and discussed. Received: 10 March 1997 / Accepted: 24 November 1997     

Human motion coordination: a juggler as an example

This paper introduces a new method for the coordination of human motion based on planning and AI techniques. Motions are considered as black boxes that are activated according to preconditions and produce postconditions in a hybrid, continuous and discrete world. Each part of the body is an autonomous entity that cooperates with the others as determined by global criteria, such as occupation rate and distance to a goal (common to all the entities). With this technique, we can easily specify and solve the motion coordination problem of a juggler that juggles with a dynamic number of balls in real time.     

A real-time vision module for interactive perceptual agents

Abstract. Interactive robotics demands real-time visual information about the environment. Real-time vision processing, however, places a heavy load on the robot's limited resources, which must accommodate multiple other processes running simultaneously. This paper describes a vision module capable of providing real-time information from ten or more operators while maintaining at least a 20-Hz frame rate and leaving sufficient processor time for a robot's other capabilities. The vision module uses a probabilistic scheduling algorithm to ensure both timely information flow and a fast frame capture. In addition, it tightly integrates the vision operators with control of a pan-tilt-zoom camera. The vision module makes its information available to other modules in the robot architecture through a shared memory structure. The information provided by the vision module includes the operator information along with a time stamp indicating information relevance. Because of this design, our robots are able to react in a timely manner to a wide variety of visual events.     

Analysis and verification of real-time systems using quantitative symbolic algorithms

The task of checking if a computer system satisfies its timing specifications is extremely important. These systems are often used in critical applications where failure to meet a deadline can have serious or even fatal consequences. This paper presents an efficient method for performing this verification task. In the proposed method a real-time system is modeled by a state-transition graph represented by binary decision diagrams. Efficient symbolic algorithms exhaustively explore the state space to determine whether the system satisfies a given specification. In addition, our approach computes quantitative timing information such as minimum and maximum time delays between given events. These results provide insight into the behavior of the system and assist in the determination of its temporal correctness. The technique evaluates how well the system works or how seriously it fails, as opposed to only whether it works or not. Based on these techniques a verification tool called Verus has been constructed. It has been used in the verification of several industrial real-time systems such as the robotics system described below. This demonstrates that the method proposed is efficient enough to be used in real-world designs. The examples verified show how the information produced can assist in designing more efficient and reliable real-time systems.     

Automatic reconstruction of 3D human arm motion from a monocular image sequence

A model-based approach to reconstruction of 3D human arm motion from a monocular image sequence taken under orthographic projection is presented. The reconstruction is divided into two stages. First, a 2D shape model is used to track the arm silhouettes and second-order curves are used to model the arm based on an iteratively reweighted least square method. As a result, 2D stick figures are extracted. In the second stage, the stick figures are backprojected into the scene. 3D postures are reconstructed using the constraints of a 3D kinematic model of the human arm. The motion of the arm is then derived as a transition between the arm postures. Applications of these results are foreseen in the analysis of human motion patterns. Received: 26 January 1996 / Accepted: 17 July 1997     

Experimenting with nonintrusive motion capture in a virtual environment

A growing number of promising applications requires recognizing human posture and motion. Conventional techniques require us to attach foreign objects to the body, which in some applications is disturbing or even impossible. New, nonintrusive motion capture approaches are called for. The well-known shape-from-silhouette technique for understanding 3D shapes could also be effective for human bodies. We present a novel technique for model-based motion capture that uses silhouettes extracted from multiple views. A 3D reconstruction of the performer can be computed from a silhouette with a technique known as volume intersection. We can recover the posture by fitting a model of the human body to the reconstructed volume. The purpose of this work is to test the effectiveness of this approach in a virtual environment by investigating the precision of the posture and motion obtained with various numbers and arrangements of stationary cameras. An average 1% position error has been obtained with five cameras.     

Creating and retargetting motion by the musculoskeletal human body model

Recently, optimization has been used in various ways to interpolate or retarget human body motions obtained by motion-capturing systems. However, in such cases, the inner structure of a human body has rarely been taken into account, and hence there have been difficulties in simulating physiological effects such as fatigue or injuries. In this paper, we propose a method to create/retarget human body motions using a musculoskeletal human body model. Using our method, it is possible to create dynamically and physiologically feasible motions. Since a muscle model based on Hill's model is included in our system, it is also possible to retarget the original motion by changing muscular parameters. For example, using the muscle fatigue model, a motion where a human body gradually gets tired can be simulated. By increasing the maximal force exertable by the muscles, or decreasing it to zero, training or displacement effects of muscles can also be simulated. Our method can be used for biomechanically correct inverse kinematics, interpolation of motions, and physiological retargetting of the human body motion.     

Secure buffering in firm real-time database systems

Many real-time database applications arise in electronic financial services, safety-critical installations and military systems where enforcing security is crucial to the success of the enterprise. We investigate here the performance implications, in terms of killed transactions, of guaranteeing multi-level secrecy in a real-time database system supporting applications with firm deadlines. In particular, we focus on the buffer management aspects of this issue. Our main contributions are the following. First, we identify the importance and difficulties of providing secure buffer management in the real-time database environment. Second, we present SABRE, a novel buffer management algorithm that provides covert-channel-free security. SABRE employs a fully dynamic one-copy allocation policy for efficient usage of buffer resources. It also incorporates several optimizations for reducing the overall number of killed transactions and for decreasing the unfairness in the distribution of killed transactions across security levels. Third, using a detailed simulation model, the real-time performance of SABRE is evaluated against unsecure conventional and real-time buffer management policies for a variety of security-classified transaction workloads and system configurations. Our experiments show that SABRE provides security with only a modest drop in real-time performance. Finally, we evaluate SABRE's performance when augmented with the GUARD adaptive admission control policy. Our experiments show that this combination provides close to ideal fairness for real-time applications that can tolerate covert-channel bandwidths of up to one bit per second (a limit specified in military standards). Received March 1, 1999 / Accepted October 1, 1999     

Realistic rendering of an organ surface in real-time for laparoscopic surgery simulation

Published online: 23 April 2002     

Robust parametric active contours: the Sandwich Snakes

Snakes are active contours that minimize an energy function. We present a new kind of active contours called “Sandwich Snakes”. They are formed by two snakes, one inside and the other outside of the curve that one is looking for. They have the same number of particles, which are connected in one-to-one correspondence. At the minimum the two snakes have the same position. We also present here a multi-scale system, where Sandwich Snakes are adjusted at increasing resolutions, and an interactive tool that permits one to easily specify the initial position for the Sandwich Snakes. Sandwich Snakes exhibit very good perfomance detecting contours with complex shapes, where the traditional methods fail. They are also very robust with respect to noise. Received: 29 January 1999 / Accepted: 20 August 2000     

Motion segmentation and pose recognition with motion history gradients

This paper presents a fast and simple method using a timed motion history image (tMHI) for representing motion from the gradients in successively layered silhouettes. This representation can be used to (a) determine the current pose of the object and (b) segment and measure the motions induced by the object in a video scene. These segmented regions are not “motion blobs”, but instead are motion regions that are naturally connected to parts of the moving object. This method may be used as a very general gesture recognition “toolbox”. We demonstrate the approach with recognition of waving and overhead clapping motions to control a music synthesis program. Accepted: 13 August 2001