OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs

TL;DR

OCDet is a lightweight, NPU-optimized object center detection framework that improves accuracy and efficiency on edge devices by introducing novel heatmap generation, loss functions, and matching techniques.

Contribution

The paper introduces OCDet, a novel object center detection method with generalized centerness, balanced focal loss, and center alignment score, optimized for edge NPUs.

Findings

OCDet outperforms YOLO11 in CAS by up to 23%.

OCDet reduces parameters by 42% and latency by 64%.

OCDet achieves up to 186% CAS improvement over keypoint methods.

Abstract

Real-time object localization on edge devices is fundamental for numerous applications, ranging from surveillance to industrial automation. Traditional frameworks, such as object detection, segmentation, and keypoint detection, struggle in resource-constrained environments, often resulting in substantial target omissions. To address these challenges, we introduce OCDet, a lightweight Object Center Detection framework optimized for edge devices with NPUs. OCDet predicts heatmaps representing object center probabilities and extracts center points through peak identification. Unlike prior methods using fixed Gaussian distribution, we introduce Generalized Centerness (GC) to generate ground truth heatmaps from bounding box annotations, providing finer spatial details without additional manual labeling. Built on NPU-friendly Semantic FPN with MobileNetV4 backbones, OCDet models are trained by our Balanced Continuous Focal Loss (BCFL), which alleviates data imbalance and focuses training on hard negative examples for probability regression tasks. Leveraging the novel Center Alignment Score (CAS) with Hungarian matching, we demonstrate that OCDet consistently outperforms YOLO11 in object center detection, achieving up to 23% higher CAS while requiring 42% fewer parameters, 34% less computation, and 64% lower NPU latency. When compared to keypoint detection frameworks, OCDet achieves substantial CAS improvements up to 186% using identical models. By integrating GC, BCFL, and CAS, OCDet establishes a new paradigm for efficient and robust object center detection on edge devices with NPUs. The code is released at https://github.com/chen-xin-94/ocdet.