BieColl - Bielefeld eCollections
Not a member yet
1004 research outputs found
Sort by
Implicit Modeling of Object Topology with Guidance from Temporal View Attention
No full textObject recognition developed to the most common approach of detecting arbitrary objects based on their appearance. However, viewpoint dependency, occlusions, algorithmic constraints, and noise are hindrances for proper object detection from a single view. As blob based segmentation cannot support learning and understanding of the object under consideration, contour based approaches are more prospective. As a consequence of aforementioned obstacles, objects are segmented often partly with more or less drop outs in contour that yields poor recognition performance. Since recognition of the "yet unknown" by the mammalian brain is supported by curiosity and experimental willingness, unknown objects are observed at least from a number of different viewpoints. These different views are considered by cognitive processes, yielding an implicit view of the object under observation. It is the objective of this paper to present an approach based on findings from biological studies and cognitive science, which enables the cognitive investigation of natural scenes and their further cognitive understanding. We proposed in another paper the architecture and a simulation of the first five bottom layers implementing the striate visual cortex as the first level of cognitive modeling of behaviors. In this work we focus on the aggregation layer, which forms object prototypes from geon recipes. The proposed implementation is exemplified again with the Necker cube
Salient Visual Features to Help Close the Loop in 6D SLAM
Full text linkOne fundamental problem in mobile robotics research is _Simultaneous Localization and Mapping_ (SLAM): A mobile robot has to localize itself in an unknown environment, and at the same time generate a map of the surrounding area. One fundamental part of SLAM algorithms is loop closing: The robot detects whether it has reached an area that has been visited before, and uses this information to improve the pose estimate in the next step. In this work, visual camera features are used to assist closing the loop in an existing 6 degree of freedom SLAM (6D SLAM) architecture. For our robotics application we propose and evaluate several detection methods, including salient region detection and maximally stable extremal region detection. The detected regions are encoded using SIFT descriptors and stored in a database. Loops are detected by matching of the images' descriptors. A comparison of the different feature detection methods shows that the combination of salient and maximally stable extremal regions suggested by Newman and Ho performs moderately
Computational Attention for Defect Localisation
Full text linkThis article deals with a biologically-motivated three-level computational attention model architecture based on the rarity and the information theory framework. It mainly focuses on a low-level step and its application in pre-attentive defect localisation for apple quality grading and tumour localisation for medical images
Free Space Estimation for Autonomous Navigation
Full text linkOne of the issue in autonomous navigation is the free space estimation. This paper presents an original framework and a method for the extraction of such an area by using a stereovision system. The _v-disparity_ algorithm is extended to provide a reliable and precise road profile on all types of roads. The free space is estimated by classifying the pixels of the disparity map. This classification is performed by using the road profile and the _u-disparity_ image. Each stage of the algorithm is presented and experimental results are shown