Pedestrian Detection
113 papers with code • 6 benchmarks • 15 datasets
Pedestrian detection is the task of detecting pedestrians from a camera.
Further state-of-the-art results (e.g. on the KITTI dataset) can be found at 3D Object Detection.
( Image credit: High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection )
Benchmarks
These leaderboards are used to track progress in Pedestrian Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Pedestrian Detection models and implementationsDatasets
CityPersons
PRW
ETH
LLVIP
INRIA Person
TJU-DHD
CADP
EuroCity Persons
RailEye3D Dataset
Latest papers
Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments
yangyanggirl/bos
•
•
However, in the real-world where test ground truths are not provided, it is non-trivial to find out whether bounding boxes are accurate, thus preventing us from assessing the detector generalization ability.
Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection
ssbin0914/Causal-Mode-Multiplexer
•
•
As a result, multispectral pedestrian detectors show poor generalization ability on examples beyond this statistical correlation, such as ROTX data.
INSANet: INtra-INter Spectral Attention Network for Effective Feature Fusion of Multispectral Pedestrian Detection
sejong-rcv/INSANet
•
•
journal 2024
Extensive experiments demonstrate the effectiveness of the proposed methods, which achieve state-of-the-art performance on the KAIST dataset and LLVIP dataset.
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Human-centric perception tasks, e. g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis.
Paved2Paradise: Cost-Effective and Scalable LiDAR Simulation by Factoring the Real World
Our key insight is that, by deliberately collecting separate "background" and "object" datasets (i. e., "factoring the real world"), we can intelligently combine them to produce a combinatorially large and diverse training set.
Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection
kimhj709/ldae
•
•
The obtained knowledge elements are adaptable to various detection frameworks, so that we can provide plentiful appearance information by integrating the language-derived appearance elements with visual cues within a detector.
DDAM-PS: Diligent Domain Adaptive Mixer for Person Search
The objective of the two bridge losses is to guide the moderate mixed-domain representations to maintain an appropriate distance from both the source and target domain representations.
HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information
This model produces a new image representation that enhances objects of interest in the scene and greatly improves detection performance.
Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors
caiyancheng/bfda
•
•
Therefore, we focus on cross-domain background feature alignment while minimizing the influence of foreground features on the cross-domain alignment stage.
An Energy-Aware Approach to Design Self-Adaptive AI-based Applications on the Edge
In this paper, we present an energy-aware approach for the design and deployment of self-adaptive AI-based applications that can balance application objectives (e. g., accuracy in object detection and frames processing rate) with energy consumption.
