We introduce a new dataset, dubbed UNICITY1, for the task of detecting people in security airlocks in top view depth images. If security companies have been relying on computer systems and algorithms for a long time, very few are trusting artificial intelligence and more specifically machine learning approaches in production environments. We are confident that the recent advances in these domains, especially with the democratization of deep learning, will open new horizons for security systems. We release this dataset to encourage the development of such approaches in the scientific community.UNICITY consists of 58k images collected from 65 recorded sequences with one or two people performing different behaviors including attacks and trickeries (e.g. tailgating2). It also provides full annotation of people such as the location of head and shoulders. As as result, UNICITY is perfectly suited for training and adapting machine learning algorithms for video surveillance applications. This paper presents the data collection, an evaluation protocol, as well as two baseline methods for attack detection.

This paper proposes a technique for spatio-temporal segmentation to identify the objects present in the scene represented in a video sequence. This technique processes two consecutive frames at a time. A region-merging approach is used to identify the objects in the scene. Starting from an oversegmentation of the current frame, the objects are formed by iteratively merging regions together. Regions are merged based on their mutual spatio-temporal similarity. We propose a modified Kolmogorov-Smirnov test for estimating the temporal similarity. The region-merging process is based on a weighted, directed graph. Two complementary graph-based clustering rules are proposed, namely, the strong rule and the weak rule. These rules take advantage of the natural structures present in the graph. Experimental results on different types of scenes demonstrate the ability of the proposed technique to automatically partition the scene into its constituent objects.

We present an improved object tracking algorithm in the context of spatio-temporal segmentation. By incorporating invariants for the spatial characterization, the information supplied by the tracking algorithm to the current segmentation is extended from a purely temporal to a more comprehensive spatio-temporal description of the objects in the scene. Thereby, the extraction and the tracking of meaningful objects in video sequences is enhanced. The proposed spatial characterization is shown to be efficiently implementable due to the additivity in feature space of the chosen class of invariants.

This paper addresses the problem of segmenting an image sequence in terms of multiple moving objects and tracking them through time and presents an object tracking algorithm. The objects are characterized through their temporal and spatial features so as to identify them and carry out the tracking procedure. The proposed tracking algorithm helps to detect the objects present in the current frame by supplying previous spatio-temporal information to the spatio-temporal segmentation procedure. In addition, the proposed algorithm tackles the correspondence problem. This is achieved through the use of a multiple hypotheses framework, the latter tests being based on both temporal and spatial characterizations of the objects.

This paper proposes a new technique to build a background memory based on mosaicking. More precisely, the technique first identifies background and foreground regions based on local motion estimates. Camera motion is then estimated on the background by applying parametric global motion estimation. Finally, after compensating for camera motion, the background content is temporally integrated in long-term memory. The method leads to high coding performances and allows for content-based functionalities.

A region merging technique for spatio-temporal segmentation of scenes is presented. The proposed technique is a bottom-up method and expects an initial set of regions. These regions are compared on the basis of a similarity measure that integrates both spatial and temporal information. The unsupervised merging procedure is based on a weighted, directed graph that is updated dynamically. Two graph based clustering rules are presented. These rules are used to cluster regions into ensembles that represent meaningful objects present in the scene. Experimental results demonstrate the efficiency of the proposed method.

In video coding, the reduction of temporal redundancy is the key to achieving high performance. In the framework of sequence coding, motion estimation and compensation has been shown to be very efficient at removing temporal redundancy. The motion existing in a scene can be mainly seen as arising from local motions superimposed to the camera motion. A new two stage global/local motion estimation approach is presented. The global motion estimation only relies on the background information. It is based on a matching technique and the global motion model is chosen to be affine. Simulation results show significant improvements obtained with the proposed method compared to the usual methods.

The problem of segmenting an image sequence in terms of regions characterized by a coherent motion is among the most challenging in image sequence analysis. This paper proposes a new technique which sequentially refines the segmentation and the motion estimation by combining static segmentation and motion information. The motion is robustly computed by a global estimation which remove the camera motion, followed by a local estimation using a matching technique and a robust estimator. Simulation results show the efficiency of the proposed technique.

The key to high performance in image sequence coding lies in an efficient reduction of the temporal redundancies. For this purpose, motion estimation and compensation techniques have been successfully applied. This paper studies motion estimation algorithms in the context of first generation coding techniques commonly used in digital TV. In this framework, estimating the motion in the scene is not an intrinsic goal. Motion estimation should indeed provide good temporal prediction and simultaneously require low overhead information. More specifically the aim is to minimize globally the bandwidth corresponding to both the prediction error information and the motion parameters. This paper first clarifies the notion of motion, reviews classical motion estimation techniques, and outlines new perspectives. Block matching techniques are shown to be the most appropriate in the framework of first generation coding. To overcome the drawbacks characteristic of most block matching techniques, this paper proposes a new locally adaptive multigrid block matching motion estimation technique. This algorithm has been designed taking into account the above aims. It leads to a robust motion field estimation precise prediction along moving edges and a decreased amount of side information in uniform areas. Furthermore, the algorithm controls the accuracy of the motion estimation procedure in order to optimally balance the amount of information corresponding to the prediction error and to the motion parameters. Experimental results show that the technique results in greatly enhanced visual quality and significant saving in terms of bit rate when compared to classical block matching techniques.>

Block matching motion estimation techniques have shown their efficiency to reduce the temporal redundancy for video coding. However, they tend to introduce annoying block artifacts in the displaced frame difference due to their block-based model. In this paper, we propose a motion field refinement technique in order to overcome these artifacts. The method relies on vector quantization. The patterns to segment the motion field are derived by the LBG algorithm, the training being performed on segmented patterns obtained from natural images. Simulation results show a significant improvement due to the proposed method, in particular moving edges are much better motion compensated and the visual quality is greatly enhanced.>

Motion estimation and compensation techniques are widely used in video coding. This paper addresses the problem of the trade-off between the motion and the prediction error information. Under some realistic hypotheses, the transmission cost of these two components can be estimated. Therefore, we obtain a criterion which controls the motion estimation process in order to optimize its performance. As a particular application, this criterion is applied to the split procedure of an adaptive multigrid block matching technique. Simulation results are presented, showing the significant improvements due to the method.

This paper introduces an improved variable size block based motion estimation algorithm relying on a hierarchy of motion representations. The most efficient of the latter is chosen through an evaluation constraint which models the total bit rate. The proposed coding technique exploits the concepts of temporal tracking and localization of the displaced frame difference energy. Moreover, only the smallest regions of the latter are coded and transmitted. Simulations show a significant improvement of the performances.