In this contribution, we present a large-scale hierarchical system for object detection fusing bottom-up (signal-driven) processing results with top-down (model or task-driven) attentional modulation. Specifically, we focus on the question of how the autonomous learning of invariant models can be embedded into a performing system and how such models can be used to define object-specific attentional modulation signals. Our system implements bi-directional data flow in a processing hierarchy. The bottom-up data flow proceeds from a preprocessing level to the hypothesis level where object hypotheses created by exhaustive object detection algorithms are represented in a roughly retinotopic way. A competitive selection mechanism is used to determine the most confident hypotheses, which are used on the system level to train multimodal models that link object identity to invariant hypothesis properties. The top-down data flow originates at the system level, where the trained multimodal models are used to obtain space- and feature-based attentional modulation signals, providing biases for the competitive selection process at the hypothesis level. This results in object-specific hypothesis facilitation/suppression in certain image regions which we show to be applicable to different object detection mechanisms. In order to demonstrate the benefits of this approach, we apply the system to the detection of cars in a variety of challenging traffic videos. Evaluating our approach on a publicly available dataset containing approximately 3,500 annotated video images from more than 1 h of driving, we can show strong increases in performance and generalization when compared to object detection in isolation. Furthermore, we compare our results to a late hypothesis rejection approach, showing that early coupling of top-down and bottom-up information is a favorable approach especially when processing resources are constrained.

Abstract-We study the problem of actively searching for an object in a 3D environment under the constraint of a maximum search time, using a visually guided humanoid robot with twentysix degrees of freedom. The inherent intractability of the problem is discussed and a greedy strategy for selecting the best next viewpoint is employed. We describe a target probability updating scheme approximating the optimal solution to the problem, providing an efficient solution to the selection of the best next viewpoint. We employ a hierarchical recognition architecture, inspired by human vision, that uses contextual cues for attending to the view-tuned units at the proper intrinsic scales and for active control of the robotic platform sensor's coordinate frame, also giving us control of the extrinsic image scale and achieving the proper sequence of pathognomonic views of the scene. The recognition model makes no particular assumptions on shape properties like texture and is trained by showing the object by hand to the robot. Our results demonstrate the feasibility of using state of the art vision-based systems for efficient and reliable object localization in an indoor 3D environment.

We present an integrated vision architecture capable of incrementally learning several visual categories based on natural hand-held objects. Additionally we focus on interactive learning, which requires real-time image processing methods and a fast learning algorithm. The overall system is composed of a figure-ground segregation part, several feature extraction methods and a life-long learning approach combining incremental learning with category-specific feature selection. In contrast to most visual categorization approaches, where typically each view is assigned to a single category, we allow labeling with an arbitrary number of shape and color categories. We also impose no restrictions on the viewing angle of presented objects, relaxing the common constraint on canonical views.

Abstract. Parts-based recognition has been suggested for generalizing from few training views in categorization scenarios. In this paper we present the results of a comparative investigation of different feature types with regard to their suitability for category discrimination. So patches of gray-scale images were compared with SIFT descriptors and patches from the high-level output of a feedforward hierarchy related to the ventral visual pathway. We discuss the conceptual differences, resulting performance and consequences for hierarchical models of visual recognition.

Abstract-A major step towards intelligent vehicles lies in the acquisition of an environmental representation of sufficient generality to serve as the basis for a multitude of different assistance-relevant tasks. This acquisition process must reliably cope with the variety of environmental changes inherent to traffic environments. As a step towards this goal, we present our most recent integrated system performing object detection in challenging environments (e.g., inner-city or heavy rain). The system integrates unspecific and vehicle-specific methods for the detection of traffic scene elements, thus creating multiple object hypotheses. Each detection method is modulated by optimized models of typical scene context features which are used to enhance and suppress hypotheses. A multi-object tracking and fusion process is applied to make the produced hypotheses spatially and temporally coherent. In extensive evaluations we show that the presented system successfully analyzes scene elements under diverse conditions, including challenging weather and changing scenarios. We demonstrate that the used generic hypothesis representations allow successful application to a variety of tasks including object detection, movement estimation, and risk assessment by time-to-contact evaluation.