Joint change-detection: how the interplay between scene context and object detection is affected by task setting

Download

index.pdf

Date

2017

Author

Akkuşcu, Mustafa

Metadata

Show full item record

Item Usage Stats

125
views

57
downloads

In this paper, we study the effects of social setting on change-detection performance: First, we investigate how detection of changing (i.e., repeatedly appearing and disappearing) objects in scene images is influenced by the scene context. If a changing object’s identity is in conflict with its surrounding context (e.g. a boat on a highway), that is a semanticallyinconsistent change; if there is no such conflict (e.g., a boat in a lake), that is a semantically-consistent change. We found, in line with previous studies in the literature, that inconsistent changes were detected more often (more accurately) and faster than the consistent ones, probably because attention was attracted towards inconsistent objects earlier than the consistent ones. Second, we investigate how joint-action settings (i.e., cooperative and competitive) affect performance on the change-detection task. Based on social facilitation literature, which indicates simple tasks are performed better and complex tasks are performed worse in the presence of others, we expect that detecting inconsistent changes (a simple task) are even more often and faster, whereas detecting consistent changes (a complex task) are even less often and more slowly in the presence of a cooperating or competing co-actor, as compared to individual condition. However, we did not find such a differential effect. Instead, our results showed that cooperating subjects performed similarly to the individual subjects; competing subjects, though detected the inconsistent changes more often than the consistent ones, were less accurate but faster on both types of change relative to the individual subjects.

Subject Keywords

Semantics., Context (Linguistics).

URI

http://etd.lib.metu.edu.tr/upload/12621556/index.pdf
https://hdl.handle.net/11511/26772

Collections

Graduate School of Informatics, Thesis

Suggestions

OpenMETU
Core

Investigation of semantic effects in oddball paradigm through event related potentials Dumlu, Seda Nilgün; Gökçay, Didem; Öniz, Adile; Department of Medical Informatics (2012) In this study, the effect of semantic information processing was investigated by the oddball paradigm, by presenting consecutive Turkish words or word-like non-words while EEG signals are recorded. In an oddball paradigm, a series of events are presented of which one class is rarer than the other. Subjects are asked to respond to the infrequent stimuli (e.g. press a button, or count the number). The event related potential (ERP) component P300 obtained from EEG is considered as the marker of this attention ...
Effect of Visual Context Information for Super Resolution Problems Akar, Gözde; Aykut, Ekin; Cengiz, Baran; Bocek, Kadircan (2019-04-26) In this study, the effect of visual context information to the performance of learning-based techniques for the super resolution problem is analyzed. Beside the interpretation of the experimental results in detail, its theoretical reasoning is also achieved in the paper. For the experiments, two different visual datasets composed of natural and remote sensing scenes are utilized. From the experimental results, we observe that keeping visual context information in the course of parameter learning for convolu...
Anomaly Detection and Activity Perception Using Covariance Descriptor for Trajectories Ergezer, Hamza; Leblebicioğlu, Mehmet Kemal (2016-10-16) In this work, we study the problems of anomaly detection and activity perception through the trajectories of objects in crowded scenes. For this purpose, we propose a novel representation for trajectories via covariance features. Representing trajectories via feature covariance matrices enables us to calculate the distance between the trajectories of different lengths. After setting this proposed representation and calculation of distances between trajectories, anomaly detection is achieved by sparse repres...
SUPER-RESOLUTION RECONSTRUCTION OF HYPERSPECTRAL IMAGES VIA AN IMPROVED MAP-BASED APPROACH Irmak, Hasan; Akar, Gözde; Yuksel, Seniha Esen; Aytaylan, Hakan (2016-07-15) Super-resolution Reconstruction (SRR) is technique to increase the spatial resolution of images. It is especially useful for hyperspectral images (HSI), which have good spectral resolution but low spatial resolution. In this study, we propose an improvement to our previous work and present a novel MAP-MRF (maximum a posteriori-Markov random Fields) based approach for the SRR of HSI. The key point of our approach is to find the abundance maps of an HSI and perform SRR on the abundance maps using MRF based en...
REAL-TIME ARBITRARY VIEW RENDERING ON GPU FROM STEREO VIDEO AND TIME-OF-FLIGHT CAMERA Ates, Tugrul K.; Alatan, Abdullah Aydın (2011-05-18) Generating in-between images from multiple views of a scene is a crucial task for both computer vision and computer graphics fields. Photorealistic rendering, 3DTV and robot navigation are some of many applications which benefit from arbitrary view synthesis, if it is achieved in real-time. GPUs excel in achieving high computation power by processing arrays of data in parallel, which make them ideal for real-time computer vision applications. This paper proposes an arbitrary view rendering algorithm by usin...

Citation Formats

M. Akkuşcu, “Joint change-detection: how the interplay between scene context and object detection is affected by task setting,” M.S. - Master of Science, Middle East Technical University, 2017.