Robert Bergevin

Towards a general multi-view registration technique

We present an algorithm that reduces significantly the level of the registration errors between all pairs in a set of range views. This algorithm refines initial estimates of the transformation matrices obtained from either the calibrated acquisition setup or a crude manual alignment. It is an instance of a category of registration algorithms known as iterated closest-point (ICP) algorithms. The algorithm considers the network of views as a whole and minimizes the registration errors of all views simultaneously. This leads to a well-balanced network of views in which the registration errors are equally distributed, an objective not met by previously published ICP algorithms which all process the views sequentially. Experimental results show that this refinement technique improves the calibrated registrations and the quality of the integrated model for complex multi-part objects. In the case of scenes comprising man-made objects of very simple shapes, the basic algorithm faces problems common to all ICP algorithms and so must be extended.

A method for the registration of attributed range images

Registration of range images requires the identification of common portions of surfaces between which a distance minimization is performed. This paper proposes a framework for the use of dense attributes of range image elements as a matching constraint in the registration. These attributes are chosen to be invariant to rigid transformations, so that their value is similar in different views of the same surface portion. Attributes can be derived from the geometry information in the range image, such as surface curvature, or be obtained from associated intensity measurements. The method is based on the Iterative Closest Compatible Point algorithm augmented with a random sampling scheme that uses the distribution of attributes as a guide for point selection. Distance minimization is performed only between pairs of points considered compatible on the basis of their attributes. The performance of the method is illustrated on a rotationally symmetric object with color patterns.

Semantic human activity recognition: A literature review

Abstract This paper presents an overview of state-of-the-art methods in activity recognition using semantic features. Unlike low-level features, semantic features describe inherent characteristics of activities. Therefore, semantics make the recognition task more reliable especially when the same actions look visually different due to the variety of action executions. We define a semantic space including the most popular semantic features of an action namely the human body (pose and poselet), attributes, related objects, and scene context. We present methods exploiting these semantic features to recognize activities from still images and video data as well as four groups of activities: atomic actions, people interactions, human–object interactions, and group activities. Furthermore, we provide potential applications of semantic approaches along with directions for future research.

Flexible Background Subtraction with Self-Balanced Local Sensitivity

Most background subtraction approaches offer decent results in baseline scenarios, but adaptive and flexible solutions are still uncommon as many require scenario-specific parameter tuning to achieve optimal performance. In this paper, we introduce a new strategy to tackle this problem that focuses on balancing the inner workings of a non-parametric model based on pixel-level feedback loops. Pixels are modeled using a spatiotemporal feature descriptor for increased sensitivity. Using the video sequences and ground truth annotations of the 2012 and 2014 CVPR Change Detection Workshops, we demonstrate that our approach outperforms all previously ranked methods in the original dataset while achieving good results in the most recent one.

Towards view-invariant gait modeling: Computing view-normalized body part trajectories

This paper proposes an approach to compute view-normalized body part trajectories of pedestrians walking on potentially non-linear paths. The proposed approach finds applications in gait modeling, gait biometrics, and in medical gait analysis. Our approach uses the 2D trajectories of both feet and the head extracted from the tracked silhouettes. On that basis, it computes the apparent walking (sagittal) planes for each detected gait half-cycle. A homography transformation is then computed for each walking plane to make it appear as if walking was observed from a fronto-parallel view. Finally, each homography is applied to head and feet trajectories over each corresponding gait half-cycle. View normalization makes head and feet trajectories appear as if seen from a fronto-parallel viewpoint, which is assumed to be optimal for gait modeling purposes. The proposed approach is fully automatic as it requires neither manual initialization nor camera calibration. An extensive experimental evaluation of the proposed approach confirms the validity of the normalization process.

Panel report: the potential of geons for generic 3-D object recognition

Biedermans introduction of geons to the vision community has spawned considerable interest in building geon-based vision systems. However, numerous issues must be addressed before such systems can make a practical contribution to machine vision. At IJCAI 1993, a group of distinguished researchers, each of whom has worked with geon-based recognition, was brought together to form a panel whose goal was to identify and discuss these issues. This paper is based on that panel discussion.

Computing and evaluating view-normalized body part trajectories

This paper proposes an approach to compute and evaluate view-normalized body part trajectories of pedestrians from monocular video sequences. The proposed approach uses the 2D trajectories of both feet and of the head extracted from the tracked silhouettes. On that basis, it segments the walking trajectory into piecewise linear segments. Finally, a normalization process is applied to head and feet trajectories over each obtained straight walking segment. View normalization makes head and feet trajectories appear as if seen from a fronto-parallel viewpoint. The latter is assumed to be optimal for gait modeling and identification purposes. The proposed approach is fully automatic as it requires neither manual initialization nor camera calibration. An extensive experimental evaluation of the proposed approach confirms the validity of the normalization process.

Body tracking in human walk from monocular video sequences

This paper proposes a method to automatically track human body parts in the context of gait modelisation and recognition. The proposed approach is based on a five points human model (head, hands, and feet) where the points are detected and tracked independently. Tracking is fully automatic (no manual initialization of the five points) since it will be used in a real-time surveillance system. Feet are detected in each frame by first finding the space between the legs in the human silhouette. The issue of feet self-occlusion is handled using optical flow and motion correspondence. Skin color segmentation is used to find hands in each frame and tracking is achieved by using a bounding box overlap algorithm. The head is defined as the mass center of a region of the upper silhouette.

Estimating the 3D rigid transformation between two range views of a complex object

Presents a method to compute the inter-frame transformation between two range image views of complex multi-part objects. No exact feature matching is attempted and no initial approximate transformation is provided. The method is naturally decomposed into two stages of initial estimation and final refinement of the transformation. A hierarchical triangulation-based surface representation provides an efficient way to select the control points at which the alignment of the two surfaces is to be evaluated. This representation also permits the selection of a manageable number of initial transformations among which at least one is to be in the parametric neighborhood of the actual transformation. Experimental results show that the computed transformation between two views of a complex multi-part object may provide angles of rotation within a fraction of a degree of the actual ones.<<ETX>>

Trajectories normalization for viewpoint invariant gait recognition

This paper proposes a method to obtain fronto-parallel (side-view) body part trajectories for a walk observed from an arbitrary view. The method is based on homography transformations computed for each gait half-cycle detected in the walk. Each homography maps the body part trajectories to a simulated side view of the walk. The proposed method is stable as the resulting normalized trajectories are not influenced by missing or omitted parts of the raw trajectories. Experiments confirm that normalized trajectories are in agreement with the ones that would be obtained from a side view.