Antoine Vacavant

A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos

Abstract Background subtraction (BS) is a crucial step in many computer vision systems, as it is first applied to detect moving objects within a video stream. Many algorithms have been designed to segment the foreground objects from the background of a sequence. In this article, we propose to use the BMC (Background Models Challenge) dataset, and to compare the 29 methods implemented in the BGSLibrary. From this large set of various BG methods, we have conducted a relevant experimental analysis to evaluate both their robustness and their practical performance in terms of processor/memory requirements.

A benchmark dataset for outdoor foreground/background extraction

Most of video-surveillance based applications use a foreground extraction algorithm to detect interest objects from videos provided by static cameras. This paper presents a benchmark dataset and evaluation process built from both synthetic and real videos, used in the BMC workshop (Background Models Challenge). This dataset focuses on outdoor situations with weather variations such as wind, sun or rain. Moreover, we propose some evaluation criteria and an associated free software to compute them from several challenging testing videos. The evaluation process has been applied for several state of the art algorithms like gaussian mixture models or codebooks.

A parametric active polygon for leaf segmentation and shape estimation

In this paper we present a system for tree leaf segmentation in natural images that combines a first, unrefined segmentation step, with an estimation of descriptors depicting the general shape of a simple leaf. It is based on a light polygonal model, built to represent most of the leaf shapes, that will be deformed to fit the leaf in the image. Avoiding some classic obstacles of active contour models, this approach gives promising results, even on complex natural photographs, and constitutes a solid basis for a leaf recognition process.

Understanding leaves in natural images - A model-based approach for tree species identification

With the aim of elaborating a mobile application, accessible to anyone and with educational purposes, we present a method for tree species identification that relies on dedicated algorithms and explicit botany-inspired descriptors. Focusing on the analysis of leaves, we developed a working process to help recognize species, starting from a picture of a leaf in a complex natural background. A two-step active contour segmentation algorithm based on a polygonal leaf model processes the image to retrieve the contour of the leaf. Features we use afterwards are high-level geometrical descriptors that make a semantic interpretation possible, and prove to achieve better performance than more generic and statistical shape descriptors alone. We present the results, both in terms of segmentation and classification, considering a database of 50 European broad-leaved tree species, and an implementation of the system is available in the iPhone application Folia.

A model-based approach for compound leaves understanding and identification

In this paper, we propose a specific method for the identification of compound-leaved tree species, with the aim of integrating it in an educational smartphone application. Our work is based on dedicated shape models for compound leaves, designed to estimate the number and shape of leaflets. A deformable template approach is used to fit these models and produce a high-level interpretation of the image content. The resulting models are later used for the segmentation of leaves in both plain and natural background images, by the use of multiple region-based active contours. Combined with other botany-inspired descriptors accounting for the morphological properties of the leaves, we propose a classification method that makes a semantic interpretation possible. Results are presented over a set of more than 1000 images from 17 European tree species, and an integration in the existing mobile application Folia1 is considered.

Leaf margins as sequences

We propose a high-level interpretation of leaf contours through CSS analysis.Leaf margins are described by an original string representation of vectorial symbols.Methods inspired from string processing are adapted to this objects.We use this spatially-rich descriptor to perform species classification.Performance is compared with state-of-the-art shape descriptors, and shows competitive results. In the context of an automated leaf identification process, the use of thorough leaf margin descriptors is essential given the importance of this criterion in the determination of the species. The spatial properties of teeth along the leaf contour are something to keep track of, which is made possible through the use of structured representations. This paper introduces a sequence representation of leaf margins where teeth are viewed as symbols of a multivariate real valued alphabet. It presents the methods developed to make use of this description for classification and implementation in a mobile tree identifying application. The results of various classification methods are compared and discussed, both in terms of species recognition and of consistency with botanical concepts.

Topological and geometrical reconstruction of complex objects on irregular isothetic grids

In this paper, we address the problem of vectorization of binary images on irregular isothetic grids The representation of graphical elements by lines is common in document analysis, where images are digitized on (sometimes very-large scale) regular grids Regardless of final application, we propose to first describe the topology of an irregular two-dimensional object with its associated Reeb graph, and we recode it with simple irregular discrete arcs The second phase of our algorithm consists of a polygonal reconstruction of this object, with discrete lines through the elementary arcs computed in the previous stage We also illustrate the robustness of our method, and discuss applications and improvements.

Comparative study of segmentation methods for tree leaves extraction

In this paper, we present a comparative study of segmentation methods, tested for an issue of tree leaves extraction. Approaches implemented include processes using thresholding, clustering, or even active contours. The observation criteria, such as the Dice index, Hamming measure or SSIM for example, allow us to highlight the performance obtained by the guided active contour algorithm that is specially dedicated to tree leaf segmentation (G. Cerutti et al., Guiding Active Contours for Tree Leaf Segmentation and Identification. ImageCLEF2011). We currently offer a dedicated segmentation tree leaf benchmark, comparing fourteen segmentation methods (ten automatic and four semi-automatic) following twenty evaluation criteria.

A combined multi-scale/irregular algorithm for the vectorization of noisy digital contours

This paper proposes and evaluates a new method for reconstructing a polygonal representation from arbitrary digital contours that are possibly damaged or coming from the segmentation of noisy data. The method consists in two stages. In the first stage, a multi-scale analysis of the contour is conducted so as to identify noisy or damaged parts of the contour as well as the intensity of the perturbation. All the identified scales are then merged so that the input data is covered by a set of pixels whose size is increased according to the local intensity of noise. The second stage consists in transforming this set of resized pixels into an irregular isothetic object composed of an ordered set of rectangular and axis-aligned cells. Its topology is stored as a Reeb graph, which allows an easy pruning of its unnecessary spurious edges. Every remaining connected part has the topology of a circle and a polygonal representation is independently computed for each of them. Four different geometrical algorithms, including a new one, are reviewed for the latter task. These vectorization algorithms are experimentally evaluated and the whole method is also compared to previous works on both synthetic and true digital images. For fair comparisons, when possible, several error measures between the reconstruction and the ground truth are given for the different techniques.

Separable Distance Transformation and Its Applications

In binary shape analysis, the distance transformation (DT) and its by-products are fundamental in many applications since they provide volumetric and metric information about the input shape. In this chapter, we present a survey on a specific approach (the dimension by dimension techniques) for the Euclidean metric and with discuss its performances and its generalizations to higher dimension or to specific grid models.