Object Counting

65 papers with code • 10 benchmarks • 24 datasets

The goal of Object Counting task is to count the number of object instances in a single image or video sequence. It has many real-world applications such as traffic flow monitoring, crowdedness estimation, and product counting.

Source: Learning to Count Objects with Few Exemplar Annotations


Use these libraries to find Object Counting models and implementations

Most implemented papers

YOLO9000: Better, Faster, Stronger

AlexeyAB/darknet CVPR 2017

On the 156 classes not in COCO, YOLO9000 gets 16. 0 mAP.

You Only Look Once: Unified, Real-Time Object Detection

AlexeyAB/darknet CVPR 2016

A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation.

Synbols: Probing Learning Algorithms with Synthetic Datasets

ElementAI/baal NeurIPS 2020

Progress in the field of machine learning has been fueled by the introduction of benchmark datasets pushing the limits of existing algorithms.

Where are the Blobs: Counting by Localization with Point Supervision

ElementAI/LCFCN ECCV 2018

However, we propose a detection-based method that does not need to estimate the size and shape of the objects and that outperforms regression-based methods.

From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting

xhp-hust-2018-2011/S-DCNet 7 Jan 2020

Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i. e., the number of population can vary in [0, inf) in theory.

CNN-based Density Estimation and Crowd Counting: A Survey

gjy3035/Awesome-Crowd-Counting 28 Mar 2020

Through our analysis, we expect to make reasonable inference and prediction for the future development of crowd counting, and meanwhile, it can also provide feasible solutions for the problem of object counting in other fields.

Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT

AlexeyAB/darknet Sensors 2021

In terms of accuracy, YOLOv4-CSP was observed as the optimal model, with an AP@0. 50 of 98%.

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

facebookresearch/ijepa CVPR 2023

This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations.

Towards perspective-free object counting with deep learning

gramuah/ccnn journal 2016

Essentially, the CCNN is formulated as a regression model where the network learns how to map the appearance of the image patches to their corresponding object density maps.

Improving Object Counting with Heatmap Regulation

littleaich/heatmap-regulation 14 Mar 2018

Adding HR to a simple VGG front-end improves performance on all these benchmarks compared to a simple one-look baseline model and results in state-of-the-art performance for car counting.