A Convolutional Feature Map based Deep Network targeted towards Traffic Detection and Classification

TL;DR

This paper presents a specialized deep neural network for traffic detection and classification, addressing domain-specific challenges with innovative data handling, feature extraction, and adaptive learning techniques to improve accuracy.

Contribution

It introduces domain-specific modifications to existing object detection networks, including a blur net, optical flow features, and covariance-based pre-conditioning, enhancing traffic detection performance.

Findings

Performance improved with data sampling tricks

Blur net effectively handles blurred real-time data

Optical flow features improve orientation detection

Abstract

This research mainly emphasizes on traffic detection thus essentially involving object detection and classification. The particular work discussed here is motivated from unsatisfactory attempts of re-using well known pre-trained object detection networks for domain specific data. In this course, some trivial issues leading to prominent performance drop are identified and ways to resolve them are discussed. For example, some simple yet relevant tricks regarding data collection and sampling prove to be very beneficial. Also, introducing a blur net to deal with blurred real time data is another important factor promoting performance elevation. We further study the neural network design issues for beneficial object classification and involve shared, region-independent convolutional features. Adaptive learning rates to deal with saddle points are also investigated and an average covariance matrix based pre-conditioned approach is proposed. We also introduce the use of optical flow features to accommodate orientation information. Experimental results demonstrate that this results in a steady rise in the performance rate.