Otto Löhlein

A multiple detector approach to low-resolution FIR pedestrian recognition

In this paper we present a recognition scheme, which is both reliable and fast. The scheme comprises the simultaneous harmonized use of three powerful detection algorithms, the hyper permutation network (HPN), a hierarchical contour matching (HCM) algorithm and a cascaded classifier approach. Each algorithm is evaluated separately and afterwards, based on the evaluation results, the fusion of the detection results is performed by a particle filter approach.

Multi-class Object Detection in Vision Systems Using a Hierarchy of Cascaded Classifiers

Boosted cascades for fast and reliable object detection for one object class were introduced by Viola et al. (2001). Using this scheme for multi-class detection requires parallel usage of multiple cascades and increases computation time. We present an extension to the cascade which examines multiple classes jointly in the first stages of the cascade. Adaboost is selecting common features for all considered object classes, which are then computed only once and thus reduce the computation time of the overall system. We also show how to define the search-window, as it needs to be adjusted to the specific objects. The multi-class capable cascade is applied to traffic scenes on rural roads where pedestrians and reflection posts are detected

Surround view pedestrian detection using heterogeneous classifier cascades

Pedestrian detection is of particular interest to the automotive domain, where an accurate estimation of a pedestrians position is the first step towards reliable collision avoidance systems. Driven by rapid advances in technology, several systems to detect pedestrians in front of a moving vehicle have been proposed in recent years. This paper introduces a novel pedestrian detection system for low-speed driving scenarios, capable of detecting pedestrians in a 360-degree fashion around the vehicle. Detected pedestrians are displayed to the driver in an intuitive way using a dynamically generated Birdss Eye View image. Furthermore, a novel classifier architecture to efficiently handle this complex application scenario is provided. By combining the processing speed of a classifier cascade with the discriminative power of a multi-stage neural network, the system achieves state of the art performance while retaining real-time capability. To keep classifier complexity low, a new feature-based inter-stage information transfer method is presented. All classifier components are compared to recent pedestrian detection approaches and evaluated on a real-world data set.

Detection and Tracking of Multiple Pedestrians in Automotive Applications

We present a method for tracking an unknown and changing number of far away pedestrians in a video stream. Multiple particle filter instances are utilized which track single pedestrians independently from each other. The tracking is guided by a cascade classifier which is integrated into the particle filter framework. In order to be able to detect hardly visible pedestrians and to filter out isolated false positives of the classifier, we developed a detection criterion for particle filters which follows the track-before-detect paradigm. The system nearly works in real time.

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.

Global positioning using a digital map and an imaging radar sensor

This contribution presents a lane estimation system for night applications which covers distances up to 140 m in rural environment. The high detection range is essential for upcoming warning systems to decide whether a detected object is on the road and thus of immediate importance for the driving task. In order to realize a robust lane detection system we present a fusion system that combines the information provided by an imaging radar system and a digital map. The digital map is used to calculate the shape of the road. Past measurements of the radar sensor are integrated over time into a local map using an egomotion estimator. A particle filter realizes the matching of the digital and local map resulting in an accurate position of the vehicle on the digital map. This positioning algorithm enables an estimation of the position of the lane in front of the vehicle at high distances.

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.

Determining Posterior Probabilities on the Basis of Cascaded Classifiers as used in Pedestrian Detection Systems

Cascaded classifiers are widely spread in automotive pedestrian detection systems. Since there has been no research on probabilistic information derivable on the basis of a cascade, these systems are limited in the sense that they only exploit the binary classification results. In contrast to that, this paper presents a mathematically founded model regarding the computation of posterior probabilities on the basis of such classifiers. This is highly relevant in respect of the further development of robust and reliable detection systems.

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.

Sensor fusion to enable next generation low cost Night Vision systems

The next generation of automotive Night Vision Enhancement systems offers automatic pedestrian recognition with a performance beyond current Night Vision systems at a lower cost. This will allow high market penetration, covering the luxury as well as compact car segments. Improved performance can be achieved by fusing a Far Infrared (FIR) sensor with a Near Infrared (NIR) sensor. However, fusing with todays FIR systems will be too costly to get a high market penetration. The main cost drivers of the FIR system are its resolution and its sensitivity. Sensor cost is largely determined by sensor die size. Fewer and smaller pixels will reduce die size but also resolution and sensitivity. Sensitivity limits are mainly determined by inclement weather performance. Sensitivity requirements should be matched to the possibilities of low cost FIR optics, especially implications of molding of highly complex optical surfaces. As a FIR sensor specified for fusion can have lower resolution as well as lower sensitivity, fusing FIR and NIR can solve performance and cost problems. To allow compensation of FIR-sensor degradation on the pedestrian detection capabilities, a fusion approach called MultiSensorBoosting is presented that produces a classifier holding highly discriminative sub-pixel features from both sensors at once. The algorithm is applied on data with different resolution and on data obtained from cameras with varying optics to incorporate various sensor sensitivities. As it is not feasible to record representative data with all different sensor configurations, transformation routines on existing high resolution data recorded with high sensitivity cameras are investigated in order to determine the effects of lower resolution and lower sensitivity to the overall detection performance. This paper also gives an overview of the first results showing that a reduction of FIR sensor resolution can be compensated using fusion techniques and a reduction of sensitivity can be compensated.