A Caltech Library Service

Target detection using saliency-based attention

Itti, Laurent and Koch, Christof (2000) Target detection using saliency-based attention. In: RTO Meeting Proceedings 45. Search and Target Acquisition. RTO Meeting Proceedings. No.45. Research and Technology Organization (NATO) , Neuilly-sur-Seine, France, pp. 3-1. ISBN 9283710355.

PDF - Accepted Version
See Usage Policy.

PDF (Pages 44-53 of full proceedings) - Published Version
See Usage Policy.

PDF (Full proceedings) - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


Most models of visual search, whether involving overt eye movements or covert shifts of attention, are based on the concept of a "saliency map", that is, an explicit two-dimensional map that encodes the saliency or conspicuity of objects in the visual environment. Competition among neurons in this map gives rise to a single winning location that corresponds to the next attended target. Inhibiting this location automatically allows the system to attend to the next most salient location. We describe a detailed computer implementation of such a scheme, focusing on the problem of combining information across modalities, here orientation, intensity and color information, in a purely stimulus-driven manner. We have successfully applied this model to a wide range of target detection tasks, using synthetic and natural stimuli. Performance has however remained difficult to objectively evaluate on natural scenes, because no objective reference was available for comparison. We here present predicted search times for our model on the Search2 database of rural scenes containing a military vehicle. Overall, we found a poor correlation between human and model search times. Further analysis however revealed that in 3/4 of the images, the model appeared to detect the target faster than humans (for comparison, we calibrated the model’s arbitrary internal time frame such that no more than 2-4 image locations were visited per second). It hence seems that this model, which had originally been designed not to find small, hidden military vehicles, but rather to find the few most obviously conspicuous objects in an image, performed as an efficient target detector on the Search2 dataset.

Item Type:Book Section
Related URLs:
URLURL TypeDescription ItemLater version
Koch, Christof0000-0001-6482-8067
Additional Information:Copyright © RTO/NATO 2000. Papers presented at the RTO Workshop organised by the Systems Concepts and Integration Panel (SCI), held in Utrecht, The Netherlands, 21-23 June 1999. We thank Dr. A. Toet from TNO-HFRI for providing us with the search2 dataset and all human data. This work was supported by NSF (Caltech ERC), NIMH, ONR and NATO.
Group:Koch Laboratory (KLAB)
Funding AgencyGrant Number
U.S. Office of Naval ResearchUNSPECIFIED
Subject Keywords:Visual attention, saliency, preattentive, inhibition of return, model, winner-take-all, bottom-up, natural scene
Other Numbering System:
Other Numbering System NameOther Numbering System ID
Series Name:RTO Meeting Proceedings
Issue or Number:45
Record Number:CaltechAUTHORS:20130816-103250017
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:40573
Deposited By: KLAB Import
Deposited On:16 Jan 2008 00:54
Last Modified:03 Mar 2020 13:01

Repository Staff Only: item control page