A New Benchmark for Consumer Visual Tracking and Apparent Demographic Estimation from RGB and Thermal Images

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 23; p. 9510
• Main Authors: Panagos, Iason-Ioannis, Giotis, Angelos P, Sofianopoulos, Sokratis, Nikou, Christophoros
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 29.11.2023
• Subjects: Age groups; Algorithms; Analysis; Associations; Benchmarking; Computer vision; Consumer goods; consumer tracking; Consumers; demographic-data estimation; Demography; Detectors; Face; Forecasts and trends; Gender; Humans; Laws, regulations and rules; Machine vision; Marketing research; Motion; motion prediction; multi-attribute classification; Neural networks; target detection; Target marketing; tracklet association; Germany; tracklet association; consumer metadata; motion prediction; target detection; multi-attribute classification; consumer tracking; demographic-data estimation
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23239510

Visual tracking and attribute estimation related to age or gender information of multiple person entities in a scene are mature research topics with the advent of deep learning techniques. However, when it comes to indoor images such as video sequences of retail consumers, data are not always adequate or accurate enough to essentially train effective models for consumer detection and tracking under various adverse factors. This in turn affects the quality of recognizing age or gender for those detected instances. In this work, we introduce two novel datasets: comprises 145 video sequences compliant to personal information regulations as far as facial images are concerned and is a set of cropped body images from each sequence that can be used for numerous computer vision tasks. We also propose an end-to-end framework which comprises CNNs as object detectors, LSTMs for motion forecasting of the tracklet association component in a sequence, along with a multi-attribute classification model for apparent demographic estimation of the detected outputs, aiming to capture useful metadata of consumer product preferences. Obtained results on tracking and age/gender prediction are promising with respect to reference systems while they indicate the proposed model's potential for practical consumer metadata extraction.