Michael Gabb

High-performance on-road vehicle detection in monocular images

This paper addresses the problem of monocular vehicle detection for forward collision warning. We present a system that is able to process large images with high speed and delivers high detection rates at only one false alarm every 100 frames.

Efficient monocular vehicle orientation estimation using a tree-based classifier

For automotive assistance systems, on-road vehicle detection is a key challenge to forward collision warning. Along with detecting existence, determining a vehicles orientation plays an important role in correctly predicting maneuvers.

Feature selection for automotive object detection tasks - A study

For object detection in monocular images, the Boosted Cascade [1] has become the standard approach for driver assistance systems. This paper studies the discriminative power of different features for common automotive object detection tasks: pedestrian and vehicle detection using infrared cameras at night, as well as pedestrian and vehicle detection in daylight conditions. It is shown that the use of intra-stage information propagation with Activation History Features (AHFs) [2] significantly speeds up the detection at the same detection rate. Thus, AHFs offer a speedup at no cost.

Intuitive visualization of vehicle distance, velocity and risk potential in rear-view camera applications

Many serious collisions on highways happen while changing lanes. One of the main causes for these accidents is the drivers incorrect assessment of the current rear traffic situation. To support the driver, we propose a framework to intuitively visualize distance, speed and risk potential of approaching vehicles in a rear-view camera application. The proposed visualization techniques are based on color coding, artificial motion blur and depth-of-field rendering, which are motivated by sensory effects of the human eye and interpreted intuitively by the human visual system. The impact on the human assessment of the moving speed of an object rendered with artificial motion enhancement is evaluated in a user study. The required distance and motion estimation of the vehicles are extracted out of monocular video images, by combining lane recognition, vehicle detection and segmentation machine vision algorithms.

Improving detector performance by learning from compressed samples

Increasing data volumes coupled with bandwidth limitations in on-board data transmission paths make data compression of automotive video signals indispensable. Since traditional image compression algorithms are solely tuned for optimal human perception, this work studies their effect on a nighttime automotive pedestrian detection system. Evaluating raw-data trained detectors on compressed video streams reveals detection rate declines for strong compression factors. On the other hand, when using image compression as training data preprocessing tool an increase in detection performance can be achieved.

State and existence estimation with out-of-sequence measurements for a collision avoidance system

As their functionality becomes more and more complex, future driver assistance systems rely on several different sensors in order to combine the advantages of different measurement principles. However, in multi-sensor fusion, measurements may arrive at the fusion unit out-of-sequence, the original order of the measurements may be lost. Whereas out-of-sequence measurement processing in state estimation has been studied extensively, their incorporation in existence estimation has not been solved in the past. This paper presents a new algorithm for state and existence estimation in time-critical applications, where out-of-sequence measurements are handled adequately. The derived algorithm is validated with real-world data from crash tests.

Night time road curvature estimation based on Convolutional Neural Networks

Detecting the road geometry at night time is an essential precondition to provide optimal illumination for the driver and the other traffic participants. In this paper we propose a novel approach to estimate the current road curvature based on three sensors: A far infrared camera, a near infrared camera and an imaging radar sensor. Various Convolutional Neural Networks with different configuration are trained for each input. By fusing the classifier responses of all three sensors, a further performance gain is achieved. To annotate the training and evaluation dataset without costly human interaction a fully automatic curvature annotation algorithm based on inertial navigation system is presented as well.

Feature-based monocular vehicle turn rate estimation from a moving platform

Vision-based driver assistance systems have great potential for preventing fatalities. This work addresses the problem of 3D monocular vehicle tracking and turn rate estimation in situations where vehicles need to be tracked along intersections and curves. To estimate the tracked vehicles turn rate, an approach based on image feature correspondences and a simplified geometric vehicle model is used. The model is robustly and efficiently fitted to the matched image features using an improved RANSAC scheme that automatically enforces physically plausible vehicle motions and speeds up the overall system at the same time. Temporal integration of the computed turn rates is performed by an Extended Kalman Filter with the bicycle motion model. Experiments with real world data show the applicability and robustness of the proposed concepts.

Convolutional Neural Networks for night-time animal orientation estimation

In rural areas, wildlife animal road crossings are a threat to both the driver and the wildlife population. Since most accidents take place at night, recent night vision driver assistance systems are supporting the driver by automatically detecting animals on infrared camera imagery. After detecting an animal on the roadside, the orientation towards the road can give a first cue for an upcoming trajectory prediction. This paper describes an novel classification-based scheme for nighttime animal orientation estimation from single infrared images. Our system classifies already detected animals, in particular deer, as being either oriented left, right or back/front. We propose an approach based on Convolutional Neural Networks which learns multiple stages of invariant features in a supervised end-to-end fashion. Experiments show that our method outperforms baseline methods like HOG/SVM or boosted Haar-stumps on this task.

Time-to-Collision Estimation in Automotive Multi-Sensor Fusion with Delayed Measurements

This paper presents a time-to-collision estimation in the context of multi-sensor fusion. Several asynchronous sensors are fused where the measurements arrive at the fusion unit out-of-sequence, i.e., some measurements are temporally more delayed than others. The adequate out-of-sequence handling is crucial for time-critical applications such as pre-crash systems. Several methods are discussed and compared with respect to accuracy and computational costs. In addition, a reduced out-of-sequence algorithm for practical application is derived. The performance of the pre-crash system is evaluated using real-world data from crash tests. To this end, a soft crash target is used with a position ground truth accurate to the centimeter and a contact sensor as temporal ground truth.