Image dataset for testing search and detection models

Abstract

Abstract. The TNO Human Factors Search -2 image dataset consists of: a set of 44 high-resolution digital color images of different complex natural scenes, the ground truth corresponding to each of these scenes, and the results of psychophysical experiments on each of these images. The images in the Search -2 dataset are a subset of a larger set that has been used in a visual search and detection experiment. Each scene (image) contains a single military vehicle that serves as a search target. The image dataset, an Excel file with the ground truth and observer data, and an extensive report describing the dataset are available on CD-ROM (requests by email to the first author). The dataset can be used to develop and validate digital metrics that compute the visual distinctness (contrast, conspicuity, or saliency) of targets in complex scenes, and models of human visual search and detection. The dataset has already been used in more than ten different studies in the literature, ranging from studies evaluating target detectability metrics to eye movement studies and attempts to model the human visual system. In addition to this work, eight other articles in this special section address the Search -2 dataset.

Computational Modeling of Foveal Target Detection

“…The images were created from 44 color slide images taken during the 1995 Distributed Interactive Simulation, Search, and Target Acquisition Fidelity field test held by the U.S. Army Communications-Electronics Command Night Vision and Electronic Sensors Directorate (Toet, Bijl, Kooi, & Valeton, 1998). The color slides were digitized at high resolution to produce a digital image of 6144 x 4096 pixels.…”

“…The original 44 images contained nine different types of tracked and wheeled U.S. and foreign military vehicles in a variety of locations, aspects, postures (including partially obscured), and lighting conditions. Ranges were from 500 to 5000 m. The original 44 images did not produce wide variation in probability of detection in search and detection test (Toet et al, 1998). The 1150 images used for model validation in this project were down sampled with low-pass filtering, cropped to 1080 x 720 pixels, and then digitally manipulated to produce a wider range of expected' observer response.…”

Integral opponent-colors features for computing visual target distinctness

“…This process is described in Ref. [18] where the gamma correction and the RGB to CIE XYZ transformation is provided, calibrated on the same screen that it was used for the experiments with human observers. This transformation is …”

“…All the images are 256;256 pixels in size. The data set can be used to validate digital metrics that compute the visual distinctness of targets in complex scenes [18].…”

“…This criterium yields a visual lobe for the identi"cation of the target. A total of 64 human observers participated in the experiment [18]. Table 1 lists, on column 2, the subjective ranking of the visual lobes for identi"cation.…”