Optimized Pedestrian Detection for Multiple and Occluded People

By Sitapa Rujikietgumjorn, Robert T. Collins. 2013

39 citations recorded by the source corpus.

We present a quadratic unconstrained binary optimization (QUBO) framework for reasoning about multiple object detections with spatial overlaps. The method maximizes an objective function composed of unary detection confidence scores and pairwise overlap constraints to determine which overlapping detections should be suppressed, and which should be kept. The framework is flexible enough to handle the problem of detecting objects as a shape covering of a foreground mask, and to handle the problem of filtering confidence weighted detections produced by a traditional sliding window object detector. In our experiments, we show that our method outperforms two existing state-of-the-art pedestrian detectors.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Soft-NMS — Improving Object Detection with One Line of Code (2017, methodology): “For special cases like pedestrian detection, a quadratic unconstrained binary optimization (QUBO) solution was proposed which uses detection scores as a unary potential and overlap between detections as a pairwise potential to obtain the optimal subset of detection boxes [27].”
Adaptive NMS: Refining Pedestrian Detection in a Crowd (2019, background): “To address pedestrian detection in a crowd, [34] proposes a quadratic unconstrained binary optimization solution to suppress detection boxes, which uses detection scores as a unary potential and overlaps between detections as a pairwise potential to produce final results.”
Detection in Crowded Scenes: One Proposal, Multiple Predictions (2020, methodology): “[30] employs Quadratic Binary Optimization to predict instances, taking advantage of the prior distribution of ground truth’s sizes.”
Individualness and Determinantal Point Processes for Pedestrian Detection (2016, methodology): “In [15], a quadratic unconstrained binary optimization (QUBO) algorithm is proposed to replace NMS.”
Bounding Box Regression With Uncertainty for Accurate Object Detection (2018, methodology): “Shown in Table 5, we compare our approach with soft-NMS and quadratic unconstrained binary optimization (QUBO [46]).”
Unconstrained Salient Object Detection via Proposal Subset Optimization (2016, background): “Unlike [37, 38], our subset optimization formulation aims to handle highly noisy proposal scores, where greedy NMS often leads to a poor detection precision rate.”