Transfer learning based distance adaptive global soft biometrics prediction in surveillance

Soft biometric prediction - including age, gender, and ethnicity - is critical in surveillance applications, yet often suffers from performance degradation as subject-to-camera distance increases. This study hypothesizes that embedding distance-awareness into the training process can mitigate such degradation and enhance model generalization across varying visual conditions. We propose a distance-adaptive, multi-task deep learning framework built upon EfficientNetB3, augmented with task-specific heads and trained progressively across four distance intervals (4m to 10m). A weighted composite loss function is employed to balance classification and regression objectives. The model is evaluated on a hybrid dataset combining the Front-View Gait (FVG) and MMV Annotated Pedestrian datasets, totaling over 19,000 samples. Experimental results demonstrate that the framework achieves up to 95% gender classification accuracy at 4 meters and retains 85% accuracy at 10 meters. Ethnicity prediction maintains an accuracy above 65%, while age estimation achieves a mean absolute error (MAE) ranging from 1.1 to 1.5 years. These findings validate the model’s robustness across distances and its superiority over conventional static learning approaches. Despite challenges such as computational overhead and annotation demands, the proposed approach offers a scalable and real-time-capable solution for distance-resilient biometric systems.