In this paper we address the problem of detecting 3D interest points (IPs) using local surface characteristics. We contribute to this field by introducing a novel approach for detection of 3D IPs directly on a surface mesh without any requirements of additional image/video information. The proposed Difference-of-Normals (DoN) 3D IP detector operates on the surface mesh, and evaluates the surface structure (curvature) locally (per vertex) in the mesh data. We present an example of application in action recognition from a sequence of 3-dimensional geometrical data, where local 3D motion descriptors, Histogram of Optical 3D Flow (HOF3D), are extracted from estimated 3D optical flow in the neighborhood of each IP and made view-invariant. Experiments on the publicly available i3DPost dataset show promising results.

Recent progress in the field of human action recognition points towards the use of Spatio-Temporal Interest Points (STIPs) for local descriptor-based recognition strategies. In this paper we present a new approach for STIP detection by applying surround suppression combined with local and temporal constraints. Our method is significantly different from existing STIP detectors and improves the performance by detecting more repeatable, stable and distinctive STIPs for human actors, while suppressing unwanted background STIPs. For action representation we use a bag-of-visual words (BoV) model of local N-jet features to build a vocabulary of visual-words. To this end, we introduce a novel vocabulary building strategy by combining spatial pyramid and vocabulary compression techniques, resulting in improved performance and efficiency. Action class specific Support Vector Machine (SVM) classifiers are trained for categorization of human actions. A comprehensive set of experiments on existing benchmark datasets, and more challenging datasets of complex scenes, validate our approach and show state-of-the-art performance.

Segmentation in the surveillance domain has to deal with shadows to avoid distortions when detecting moving objects. Most segmentation approaches dealing with shadow detection are typically restricted to penumbra shadows. Therefore, such techniques cannot cope well with umbra shadows. Consequently, umbra shadows are usually detected as part of moving objects. In this paper we present a novel technique based on gradient and colour models for separating chromatic moving cast shadows from detected moving objects. Firstly, both a chromatic invariant colour cone model and an invariant gradient model are built to perform automatic segmentation while detecting potential shadows. In a second step, regions corresponding to potential shadows are grouped by considering “a bluish effect” and an edge partitioning. Lastly, (i) temporal similarities between textures and (ii) spatial similarities between chrominance angle and brightness distortions are analysed for all potential shadow regions in order to finally identify umbra shadows. Unlike other approaches, our method does not make any a-priori assumptions about camera location, surface geometries, surface textures, shapes and types of shadows, objects, and background. Experimental results show the performance and accuracy of our approach in different shadowed materials and illumination conditions.

This paper presents a method for automatic recognition of human gestures. The method works with 3D image data from a range camera to achieve invariance to viewpoint. The recognition is based solely on motion from characteristic instances of the gestures. These instances are denoted 3D motion primitives. The method extracts 3D motion from range images and represent the motion from each input frame in a view invariant manner using harmonic shape context. The harmonic shape context is classified as a 3D motion primitive. A sequence of input frames results in a set of primitives that are classified as a gesture using a probabilistic edit distance method. The system has been trained on frontal images (0deg camera rotation) and tested on 240 video sequences from 0deg and 45deg. An overall recognition rate of 82.9% is achieved. The recognition rate is independent of the viewpoint which shows that the method is indeed view invariant.