Attending to Motion: Localizing and Classifying Motion Patterns in Image Sequences

Tsotsos, John K.; Pomplun, Marc; Liu, Yueju; Martinez‐Trujillo, Julio; Simine, Evgueni

doi:10.1007/3-540-36181-2_44

Cited by 9 publications

(11 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5. The executive controller and working memory, the motion pathway (V1, MT, MST, and 7a), the peripheral target area PO, the gaze WTA and gaze controller have all been implemented and examples of performance can be found in [2,14,35,46,47]. Work is currently underway to extend the implementation to the object pathway (V1, V2, V4, and IT) and to binocular stimuli as well as extensions of the executive controller and recognition layers.…”

Section: The Simulationmentioning

confidence: 99%

See 1 more Smart Citation

Attending to visual motion

Tsotsos

Liu

Martinez‐Trujillo

et al. 2005

Computer Vision and Image Understanding

Self Cite

View full text Add to dashboard Cite

Visual motion analysis has focused on decomposing image sequences into their component features. There has been little success at re-combining those features into moving objects. Here, a novel model of attentive visual motion processing is presented that addresses both decomposition of the signal into constituent features as well as the re-combination, or binding, of those features into wholes. A new feed-forward motion-processing pyramid is presented motivated by the neurobiology of primate motion processes. On this structure the Selective Tuning (ST) model for visual attention is demonstrated. There are three main contributions: (1) a new feed-forward motion processing hierarchy, the first to include a multi-level decomposition with local spatial derivatives of velocity; (2) examples of how ST operates on this hierarchy to attend to motion and to localize and label motion patterns; and (3) a new solution to the feature binding problem sufficient for grouping motion features into coherent object motion. Binding is accomplished using a top-down selection mechanism that does not depend on a single location-based saliency representation.

show abstract

Section: The Simulationmentioning

confidence: 99%

“…The next section will detail the feed-forward motion-processing network. Earlier versions of this network appear in [13,14]. Following this, an overview of ST is provided because this structure is imposed upon the feed-forward network.…”

Section: Introductionmentioning

confidence: 99%

Attending to visual motion

Tsotsos

Liu

Martinez‐Trujillo

et al. 2005

Computer Vision and Image Understanding

Self Cite

View full text Add to dashboard Cite

show abstract

“…In Ref. 8, the authors confirm the relevance of motion in computational modeling of visual attention. In Ref.…”

Section: Introductionmentioning

confidence: 79%

Motion integration in visual attention models for predicting simple dynamic scenes

et al. 2007

View full text Add to dashboard Cite

Visual attention models mimic the ability of a visual system, to detect potentially relevant parts of a scene. This process of attentional selection is a prerequisite for higher level tasks such as object recognition. Given the high relevance of temporal aspects in human visual attention, dynamic information as well as static information must be considered in computer models of visual attention. While some models have been proposed for extending to motion the classical static model, a comparison of the performances of models integrating motion in different manners is still not available. In this article, we present a comparative study of various visual attention models combining both static and dynamic features. The considered models are compared by measuring their respective performance with respect to the eye movement patterns of human subjects. Simple synthetic video sequences, containing static and moving objects, are used to assess the model suitability. Qualitative and quantitative results provide a ranking of the different models.

show abstract

“…The selective tuning is a more flexible architecture than the WTA process in (Koch and Ullman 1984), which is motivated from neurobiological findings. In (Tsotsos, Pomplum, Liu, Martinez-Trujillo, and Simine 2002) this model is developed further to approximate the neural processing of translation-, rotation-, and growing-motion of humans.…”

Section: Winner-take-allmentioning

confidence: 99%

Visual Attention Using Game Theory

Ramström

Christensen

2002

Biologically Motivated Computer Vision

View full text Add to dashboard Cite

The question "what is on the table?" is normally simple for a human, but difficult for a machine. The problem is that the machine does not know what to search for, as no visual properties of the targets are known. Machine-vision algorithms, in general, need explicit knowledge of visual properties to perform object detection. Moreover, several visual properties must be considered to provide robustness. Such requirements make object detection computationally demanding and hence common algorithms scale poorly with respect to the number of objects and their visual properties. To address these problems a system has been developed that is inspired by findings from experimental psychology. The system is designed to search for objects on a specified place, e.g. things on a table or obstacles on a road. For such tasks many visual properties need to be processed. The presented system distributes the processing of visual properties and integrates only a relevant subset of the processed data. The relevant subset of data is found by forming object hypotheses from homogeneous regions in the scene. Hence the complexity of integrating a large set of visual properties is reduced.This thesis first provides a survey of findings from experimental psychology, which give insight into the strategies used by the human visual system. From this survey it is clear that the processing of visual data is distributed across our visual cortex. Attentional mechanisms cooperate to fuse only a relevant subset of the data. One example of such mechanisms is object formation.The presented system is also inspired by game theory, a field in which distributed computing and cooperation has been studied for quite some time. This thesis provides an overview of game theory and evaluates its applicability to visual attention.The system is evaluated in the context of a tabletop scenario; detecting objects on a table in a natural environment. The evaluation demonstrates that a sparse set of data is indeed enough for object detection when the visual context is known and the scene not too cluttered. iv v SammanfattningFrågan "vad finns på bordet?" är vanligtvis enkel för en människa men svår för en dator. Problemet för datorn är att den inte vet vad den ska leta efter; den vet inte vilka visuella egenskaper de sökta objekten har. I allmänhet behöver datorseendealgoritmer explicit kunskap om visuella egenskaper för objektdetektion. Dessutom behövs många visuella egenskaper beaktas för att ge robusthet. Sådana krav gör algoritmer för objektdetektion beräkningsinten-siva och begränsar deras skalbarhet med avseende på antal objekt och deras visuella egenskaper. Ett system som angriper dessa problem har utvecklats. Systemet är inspirerat av experimentell psykologi och är ämnat att söka efter objekt på ett specificerat ställe; t ex saker på ett bord eller hinder på en väg. Beräkningarna av visuella egenskaper är distribuerade och endast en relevant delmängd av data integreras. Den relevanta delmängden identifieras genom att forma objekthypoteser från homogena ytor i ...

show abstract

Attending to Motion: Localizing and Classifying Motion Patterns in Image Sequences

Cited by 9 publications

References 50 publications

Attending to visual motion

Attending to visual motion

Motion integration in visual attention models for predicting simple dynamic scenes

Visual Attention Using Game Theory

Contact Info

Product

Resources

About