Tracking natural trails with swarm-based visual saliency

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

This paper proposes a model for trail detection and tracking that builds upon the observation that trails are salient structures in the robot's visual field. Due to the complexity of natural environments, the straightforward application of bottom-up visual saliency models is not sufficiently robust to predict the location of trails. As for other detection tasks, robustness can be increased by modulating the saliency computation based on a priori knowledge about which pixel-wise visual features are most representative of the object being sought. This paper proposes the use of the object's overall layout as the primary cue instead, as it is more stable and predictable in natural trails. Bearing in mind computational parsimony and detection robustness, this knowledge is specified in terms of perception-action rules, which control the behavior of simple agents performing as a swarm to compute the saliency map of the input image. For the purpose of tracking, multiframe evidence about the trail location is obtained with a motion-compensated dynamic neural field. In addition, to reduce ambiguity between the trail and trail-like distractors, a simple appearance model is learned online and used to influence the agents' activity. Experimental results on a large data set reveal the ability of the model to produce a success rate on the order of 97% at 20 Hz. The model is shown to be robust in situations where previous models would fail, such as when the trail does not emerge from the lower part of the image or when it is considerably interrupted.
Original languageEnglish
Pages (from-to)64-86
JournalJournal Of Field Robotics
Volume30
Issue number1
DOIs
Publication statusPublished - 1 Jan 2013

Fingerprint

Pixels
Robots

Keywords

    Cite this

    @article{f77888dcab7446919e33cbafdf12bc0c,
    title = "Tracking natural trails with swarm-based visual saliency",
    abstract = "This paper proposes a model for trail detection and tracking that builds upon the observation that trails are salient structures in the robot's visual field. Due to the complexity of natural environments, the straightforward application of bottom-up visual saliency models is not sufficiently robust to predict the location of trails. As for other detection tasks, robustness can be increased by modulating the saliency computation based on a priori knowledge about which pixel-wise visual features are most representative of the object being sought. This paper proposes the use of the object's overall layout as the primary cue instead, as it is more stable and predictable in natural trails. Bearing in mind computational parsimony and detection robustness, this knowledge is specified in terms of perception-action rules, which control the behavior of simple agents performing as a swarm to compute the saliency map of the input image. For the purpose of tracking, multiframe evidence about the trail location is obtained with a motion-compensated dynamic neural field. In addition, to reduce ambiguity between the trail and trail-like distractors, a simple appearance model is learned online and used to influence the agents' activity. Experimental results on a large data set reveal the ability of the model to produce a success rate on the order of 97{\%} at 20 Hz. The model is shown to be robust in situations where previous models would fail, such as when the trail does not emerge from the lower part of the image or when it is considerably interrupted.",
    keywords = "ROADS, ATTENTION, NAVIGATION, SELECTION, AGENT, IMAGE, ROBOT, VISION, DYNAMICS, COGNITION",
    author = "{Barata Oliveira}, {Jos{\'e} Ant{\'o}nio} and Ricardo Mendonca",
    note = "Sem pdf conforme despacho",
    year = "2013",
    month = "1",
    day = "1",
    doi = "10.1002/rob.21423",
    language = "English",
    volume = "30",
    pages = "64--86",
    journal = "Journal Of Field Robotics",
    issn = "1556-4959",
    publisher = "John Wiley & Sons",
    number = "1",

    }

    Tracking natural trails with swarm-based visual saliency. / Barata Oliveira, José António; Mendonca, Ricardo.

    In: Journal Of Field Robotics, Vol. 30, No. 1, 01.01.2013, p. 64-86.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Tracking natural trails with swarm-based visual saliency

    AU - Barata Oliveira, José António

    AU - Mendonca, Ricardo

    N1 - Sem pdf conforme despacho

    PY - 2013/1/1

    Y1 - 2013/1/1

    N2 - This paper proposes a model for trail detection and tracking that builds upon the observation that trails are salient structures in the robot's visual field. Due to the complexity of natural environments, the straightforward application of bottom-up visual saliency models is not sufficiently robust to predict the location of trails. As for other detection tasks, robustness can be increased by modulating the saliency computation based on a priori knowledge about which pixel-wise visual features are most representative of the object being sought. This paper proposes the use of the object's overall layout as the primary cue instead, as it is more stable and predictable in natural trails. Bearing in mind computational parsimony and detection robustness, this knowledge is specified in terms of perception-action rules, which control the behavior of simple agents performing as a swarm to compute the saliency map of the input image. For the purpose of tracking, multiframe evidence about the trail location is obtained with a motion-compensated dynamic neural field. In addition, to reduce ambiguity between the trail and trail-like distractors, a simple appearance model is learned online and used to influence the agents' activity. Experimental results on a large data set reveal the ability of the model to produce a success rate on the order of 97% at 20 Hz. The model is shown to be robust in situations where previous models would fail, such as when the trail does not emerge from the lower part of the image or when it is considerably interrupted.

    AB - This paper proposes a model for trail detection and tracking that builds upon the observation that trails are salient structures in the robot's visual field. Due to the complexity of natural environments, the straightforward application of bottom-up visual saliency models is not sufficiently robust to predict the location of trails. As for other detection tasks, robustness can be increased by modulating the saliency computation based on a priori knowledge about which pixel-wise visual features are most representative of the object being sought. This paper proposes the use of the object's overall layout as the primary cue instead, as it is more stable and predictable in natural trails. Bearing in mind computational parsimony and detection robustness, this knowledge is specified in terms of perception-action rules, which control the behavior of simple agents performing as a swarm to compute the saliency map of the input image. For the purpose of tracking, multiframe evidence about the trail location is obtained with a motion-compensated dynamic neural field. In addition, to reduce ambiguity between the trail and trail-like distractors, a simple appearance model is learned online and used to influence the agents' activity. Experimental results on a large data set reveal the ability of the model to produce a success rate on the order of 97% at 20 Hz. The model is shown to be robust in situations where previous models would fail, such as when the trail does not emerge from the lower part of the image or when it is considerably interrupted.

    KW - ROADS

    KW - ATTENTION

    KW - NAVIGATION

    KW - SELECTION

    KW - AGENT

    KW - IMAGE

    KW - ROBOT

    KW - VISION

    KW - DYNAMICS

    KW - COGNITION

    U2 - 10.1002/rob.21423

    DO - 10.1002/rob.21423

    M3 - Article

    VL - 30

    SP - 64

    EP - 86

    JO - Journal Of Field Robotics

    JF - Journal Of Field Robotics

    SN - 1556-4959

    IS - 1

    ER -