[show abstract][hide abstract] ABSTRACT: We present an efficient method for detecting planar bilateral symmetries under perspective projection. The method uses local
affine frames (LAFs) constructed on maximally stable extremal regions or any other affine covariant regions detected in the
image to dramatically improve the process of detecting symmetric objects under perspective distortion. In contrast to the
previous work no Hough transform, is used. Instead, each symmetric pair of LAFs votes just once for a single axis of symmetry.
The time complexity of the method is n log(n), where n is the number of LAFs, allowing a near real-time performance. The proposed method is robust to background clutter and partial
occlusion and is capable of detecting an arbitrary number of symmetries in the image.
[show abstract][hide abstract] ABSTRACT: A new method is presented for detecting planar rota- tional symmetry under affine projection. The method can deal with partial occlusion and is able to detect multiple ro- tationally symmetric surfaces in complex backgrounds. The order of rotational symmetry can be estimated, and if it is greater than two, the tilt and orientation of the rotationally symmetric surface can be found and the symmetric region segmented. Local features robust to local affine distortion are matched to obtain pairs of features. Each feature pair hypothesises a set of centres of rotation for different tilts and orientations and the centres of rotation that are close to each other are grouped together to find the dominant rotational symmetries in the image. The method is posed independently of a specific feature detector and descriptor. Results are presented on natural images.
18th International Conference on Pattern Recognition (ICPR 2006), 20-24 August 2006, Hong Kong, China; 01/2006
[show abstract][hide abstract] ABSTRACT: A method is presented for efficiently detecting bilateral sym-metry on planar surfaces under perspective projection. The method is able to detect local or global symmetries, lo-cate symmetric surfaces in complex backgrounds, and de-tect multiple incidences of symmetry. Symmetry is simulta-neously evaluated across all locations, scales, orientations and under perspective skew. Feature descriptors robust to local affine distortion are used to match pairs of symmetric features. Feature quadruplets are then formed from these symmetric feature pairs. Each quadruplet hypothesises a locally planar 3D symmetry that can be extracted under perspective distortion. The method is posed independently of a specific feature detector or descriptor. Results are pre-sented demonstrating the efficacy of the method for detect-ing bilateral symmetry under perspective distortion. Our unoptimised Matlab implementation, running on a standard PC, requires of the order of 20 seconds to process images with 1,000 feature points.
[show abstract][hide abstract] ABSTRACT: Object recognition and pose estimation are of significant importance for robotic visual servoing, manipulation and grasping tasks. Traditionally, contour and shape based methods have been considered as most adequate for estimating stable and feasible grasps (Bicchi and Kumar, 2000). A new research direction has been advocated in visual servoing where image moments are used to define a suitable error function to be minimized. Compared to appearance based methods, contour and shape based approaches are also suitable for use with range sensors such as, for example, lasers. In this paper, we evaluate a contour based object recognition system building on the method in Nelson and Selinger (1998), suitable for objects of uniform color properties such as cups, cutlery, fruits etc. This system is one of the building blocks of a more complex object recognition system based both on stereo and appearance cues, (Bjorkman and Kragic, 2004). The system has a significant potential both in terms of service robot and programming by demonstration tasks. Experimental evaluation shows promising results in terms of robustness to occlusion and noise
[show abstract][hide abstract] ABSTRACT: This paper describes a method for accurate dense reconstruction of a complex scene from a small set of high-resolution unorganized
still images taken by a hand-held digital camera. A fully automatic data processing pipeline is proposed. Highly discriminative
features are first detected in all images. Correspondences are then found in all image pairs by wide-baseline stereo matching
and used in a scene structure and camera reconstruction step that can cope with occlusion and outliers. Image pairs suitable
for dense matching are automatically selected, rectified and used in dense binocular matching. The dense point cloud obtained
as the union of all pairwise reconstructions is fused by local approximation using oriented geometric primitives. For texturing,
every primitive is mapped on the image with the best resolution.
The global structure reconstruction in the first step allows us to work with an unorganized set of images and to avoid error
accumulation. By using object-centered geometric primitives we are able to preserve the flexibility of the method to describe
complex free-form structures, preserve the possibility to build the dense model in an incremental way, and to retain the possibility
to refine the cameras and the dense model by bundle adjustment. Results are demonstrated on partial models of a circular church
and a Henri de Miller’s sculpture. We observed spatial resolution in the range of centimeters on objects of about 20 m in