N. Apostoloff

University of Oxford, Oxford, ENG, United Kingdom

Are you N. Apostoloff?

Claim your profile

Publications (10)4.79 Total impact

  • Source
    Nicholas Apostoloff, Andrew W. Fitzgibbon
    [Show abstract] [Hide abstract]
    ABSTRACT: The problem of figure-ground segmentation is of great importance in both video edit- ing and visual perception tasks. Classical video segmentation algorithms approach the problem from one of two perspectives. At one extreme, global approaches con- strain the camera motion to simplify the image structure. At the other extreme, local approaches estimate motion in small image regions over a small number of frames and tend to produce noisy signals that are difficult to segment. With recent advances in image segmentation showing that sparse information is often sufficient for figure- ground segmentation it seems surprising then that with the extra temporal informa- tion of video, an unconstrained automatic figure-ground segmentation algorithm still eludes the research community. In this paper we present an automatic video segmen- tation algorithm that is intermediate between these two extremes and uses spatiotem- poral features to regularize the segmentation. Detecting spatiotemporal T-junctions that indicate occlusion edges, we learn an occlusion edge model that is used within a colour contrast sensitive MRF to segment individual frames of a video sequence. T-junctions are learnt and classified using a support vector machine and a Gaussian mixture model is fitted to the (foreground, background) pixel pairs sampled from the detected T-junctions. Graph cut is then used to segment each frame of the video showing that sparse occlusion edge information can automatically initialize the video segmentation problem.
    Proceedings of the British Machine Vision Conference 2006, Edinburgh, UK, September 4-7, 2006; 01/2006
  • Source
    N. Apostoloff, A. Fitzgibbon
    [Show abstract] [Hide abstract]
    ABSTRACT: The goal of motion segmentation and layer extraction can be viewed as the detection and localization of occluding surfaces. A feature that has been shown to be a particularly strong indicator of occlusion, in both computer vision and neuroscience, is the T-junction; however, little progress has been made in T-junction detection. One reason for this is the difficulty in distinguishing false T-junctions (i.e. those not on an occluding edge) and real T-junctions in cluttered images. In addition to this, their photometric profile alone is not enough for reliable detection. This paper overcomes the first problem by searching for T-junctions not in space, but in space-time. This removes many false T-junctions and creates a simpler image structure to explore. The second problem is mitigated by learning the appearance of T-junctions in these spatiotemporal images. An RVM T-junction classifier is learnt from hand-labelled data using SIFT to capture its redundancy. This detector is then demonstrated in a novel occlusion detector that fuses Canny edges and T-junctions in the spatiotemporal domain to detect occluding edges in the spatial domain.
    Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on; 07/2005
  • N Apostoloff, A ~W Fitzgibbon
    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 01/2005
  • Source
    N. Apostoloff, A. Fitzgibbon
    [Show abstract] [Hide abstract]
    ABSTRACT: Video matting, or layer extraction, is a classic inverse problem in computer vision that involves the extraction of foreground objects, and the alpha mattes that describe their opacity, from a set of images. Modem approaches that work with natural backgrounds often require user-labelled "trimaps" that segment each image into foreground, background and unknown regions. For long sequences, the production of accurate trimaps can be time consuming. In contrast, another class of approach depends on automatic background extraction to automate the process, but existing techniques do not make use of spatiotemporal consistency, and cannot take account of operator hints such as trimaps. This paper presents a method inspired by natural image statistics that cleanly unifies these approaches. A prior is learnt that models the relationship between the spatiotemporal gradients in the image sequence and those in the alpha mattes. This is used in combination with a learnt foreground colour model and a prior on the alpha distribution to help regularize the solution and greatly improve the automatic performance of such systems. The system is applied to several real image sequences that demonstrate the advantage that the unified approach can afford.
    Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on; 01/2004
  • Source
    Nicholas Apostoloff, Alexander Zelinsky
    [Show abstract] [Hide abstract]
    ABSTRACT: million people die in road crashes around the world each year. It is estimated that up to 30% of these fatalities are caused by fatigue and inattention. This paper presents preliminary results of an Intelligent Transport System (ITS) project that has fused visual lane tracking and driver monitoring technologies in the rst step to closing the loop between vision inside and outside the vehicle. Ex- perimental results of the active stereo-vision lane tracking system will be discussed focusing on the particle lter and cue fusion technology used. The results from the integration of the lane tracker and the driver monitoring system are presented with an analysis of the driver's visual behavior in several dierent scenarios.
    The International Journal of Robotics Research 01/2004; 23:513-538. · 2.86 Impact Factor
  • L. Petersson, N. Apostoloff, A. Zelinsky
    [Show abstract] [Hide abstract]
    ABSTRACT: About 1.17 million people die in road crashes around the world each year. It is estimated that up to 30% of these fatalities are caused by fatigue and inattention. There are systems able to detect what is happening outside of the car, e.g., lane tracking, obstacle detection, pedestrian detection etc. Further on, there are also means for monitoring the actions of the driver. A natural step is to fuse the available data from within and outside of the car, and suggest a suitable response. This paper discusses driver assistance systems, lists a set of necessary core competencies of such a system and in particular presents a system for force-feedback in the steering wheel when crossing lanes. The presented system utilises a robust lane tracker which is experimentally evaluated for the purpose of driver assistance. In addition, preliminary results from simultaneous driver monitoring and lane tracking are presented that indicates a good correlation between the two, i.e. the driver's gaze direction and the structure of the road. These data can in turn be used for more advanced driver assistance systems in the future.
    Robotics and Automation, 2003. Proceedings. ICRA '03. IEEE International Conference on; 10/2003
  • Source
    N. Apostoloff, A. Zelinsky
    [Show abstract] [Hide abstract]
    ABSTRACT: One of the more startling effects of road related accidents is the economic and social burden they cause. Between 750,000 and 880,000 people died globally in road related accidents in 1999 alone, with an estimated cost of US$518 billion. One way of combating this problem is to develop Intelligent Vehicles that are self-aware and act to increase the safety of the transportation system. This paper presents the development and application of a novel multiple-cue visual lane tracking system for research into Intelligent Vehicles (IV). Particle filtering and cue fusion technologies form the basis of the lane tracking system which robustly handles several of the problems faced by previous lane tracking systems such as shadows on the road, unreliable lane markings, dramatic lighting changes and discontinuous changes in road characteristics and types. Experimental results of the lane tracking system running at 15 Hz will be discussed, focusing on the particle filter and cue fusion technology used.
    Intelligent Vehicles Symposium, 2003. Proceedings. IEEE; 07/2003
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: At the Australian National University's Intelligent Vehicle Project, we are developing subsystems for: driver fatigue or inattention detection; pedestrian spotting; blind-spot checking and merging assistance to validate whether sufficient clearance exists between cars; driver feedback for lane keeping; computer-augmented vision (that is, lane boundary or vehicle highlighting on a head-up display); traffic sign detection and recognition; and human factors research aids Systems that perform such supporting tasks are generally called driver assistance systems (DAS). We believe that implementing DAS could prevent similar accidents or at least reduce their severity.
    Intelligent Systems, IEEE 06/2003; · 1.93 Impact Factor
  • Source
    G. Loy, L. Fletcher, N. Apostoloff, A. Zelinsky
    [Show abstract] [Hide abstract]
    ABSTRACT: A vision system is demonstrated that adaptively allocates computational resources over multiple cues to robustly track a target in 3D. The system uses a particle filter to maintain multiple hypotheses of the target location. Bayesian probability theory provides the framework for sensor fusion, and resource scheduling is used to intelligently allocate the limited computational resources available across the suite of cues. The system is shown to track a person in 3D space moving in a cluttered environment.
    Automatic Face and Gesture Recognition, 2002. Proceedings. Fifth IEEE International Conference on; 06/2002
  • Source
    Gareth Loy, Luke Fletcher, Nicholas Apostoloff, Er Zelinsky
    [Show abstract] [Hide abstract]
    ABSTRACT: A vision system is demonstrated that adaptively allocates computational resources over multiple cues to robustly track a target in 3D. The system uses a particle filter to maintain multiple hypotheses of the target location. Bayesian probability theory provides the framework for sensor fusion, and resource scheduling is used to intelligently allocate the limited computational resources available across the suite of cues. The system is shown to track a person in 3D space moving in a cluttered environment.
    03/2002;

Publication Stats

331 Citations
4.79 Total Impact Points

Institutions

  • 2003–2005
    • University of Oxford
      • Department of Engineering Science
      Oxford, ENG, United Kingdom
  • 2002–2003
    • Australian National University
      Canberra, Australian Capital Territory, Australia