A Full-Stage Refined Proposal Algorithm for Suppressing False Positives in Two-Stage CNN-Based Detection Methods

2025-08-02

AI Summary

To address the high false positive rate and lack of end-to-end co-optimization across training and inference stages in two-stage CNN-based pedestrian detection, this paper proposes a full-stage false detection suppression algorithm. During training, a proposal verification mechanism dynamically selects high-quality candidate bounding boxes. During inference, a classifier-guided confidence recalibration scheme and vertical block-wise proposal refinement strategy are introduced to enhance proposal quality. The method integrates proposal generation, multi-classifier ensemble, and sub-region feature re-evaluation, establishing a closed-loop optimization between training and inference. Extensive experiments on Caltech, CityPersons, and our newly constructed SY-Metro dataset demonstrate a significant average reduction of 23.6% in false detection rate. Moreover, real-time performance and deployment feasibility are validated on embedded platforms such as Jetson Nano.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

False positives in pedestrian detection remain a challenge that has yet to be effectively resolved. To address this issue, this paper proposes a Full-stage Refined Proposal (FRP) algorithm aimed at eliminating these false positives within a two-stage CNN-based pedestrian detection framework. The main innovation of this work lies in employing various pedestrian feature re-evaluation strategies to filter out low-quality pedestrian proposals during both the training and testing stages. Specifically, in the training phase, the Training mode FRP algorithm (TFRP) introduces a novel approach for validating pedestrian proposals to effectively guide the model training process, thereby constructing a model with strong capabilities for false positive suppression. During the inference phase, two innovative strategies are implemented: the Classifier-guided FRP (CFRP) algorithm integrates a pedestrian classifier into the proposal generation pipeline to yield high-quality proposals through pedestrian feature evaluation, and the Split-proposal FRP (SFRP) algorithm vertically divides all proposals, sending both the original and the sub-region proposals to the subsequent subnetwork to evaluate their confidence scores, filtering out those with lower sub-region pedestrian confidence scores. As a result, the proposed algorithm enhances the model's ability to suppress pedestrian false positives across all stages. Various experiments conducted on multiple benchmarks and the SY-Metro datasets demonstrate that the model, supported by different combinations of the FRP algorithm, can effectively eliminate false positives to varying extents. Furthermore, experiments conducted on embedded platforms underscore the algorithm's effectiveness in enhancing the comprehensive pedestrian detection capabilities of the small pedestrian detector in resource-constrained edge devices.

Problem

• Reducing false positives in CNN-based pedestrian detection
• Enhancing pedestrian feature re-evaluation during training and testing
• Improving detection accuracy on resource-constrained edge devices

Innovation

• Full-stage Refined Proposal algorithm for false positives
• Training mode FRP validates proposals for model training
• Classifier-guided and Split-proposal FRP enhance inference accuracy