A method for counting moving and stationary people by interest point classification

Jeong, Chi Yoon; Choi, Su-Gil; Han, Seung Wan

doi:10.1109/icip.2013.6738936

Cited by 13 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To name a few, [31] proposed a system based on learning person appearance models, whereas [2] used hierarchical Gaussian Process Latent Variable Models (hGPLVM) for modeling people. Other approaches were based on face detection [10] or interest point classification [20]. In recent years, improvements in technology and the availability of large annotated image datasets such as Imagenet [23] have allowed Deep Neural Networks (DNNs) to become the state-of-the-art solutions for tasks such as object detection [33], segmentation [8] and classification [19] in RGB images.…”

Section: Introduction and State Of The Artmentioning

confidence: 99%

DPDnet: A robust people detector using deep learning with an overhead depth camera

Fuentes-Jimenez

Martín-López

Losada

et al. 2020

Expert Systems with Applications

View full text Add to dashboard Cite

In this paper we propose a method based on deep learning that detects multiple people from a single overhead depth image with high reliability. Our neural network, called DPDnet, is based on two fully-convolutional encoder-decoder neural blocks based on residual layers. The main block takes a depth image as input and generates a pixel-wise confidence map, where each detected person in the image is represented by a Gaussian-like distribution. The refinement block combines the depth image and the output from the main block, to refine the confidence map. Both blocks are simultaneously trained end-to-end using depth images and head position labels.The experimental work shows that DPDnet outperforms state-of-the-art methods, with accuracies greater than 99% in three different publicly available datasets, without retraining not fine-tuning. In addition, the computational complexity of our proposal is independent of the number of people in the scene and runs in real time using conventional GPUs.

show abstract

Section: Introduction and State Of The Artmentioning

confidence: 99%

DPDnet: A robust people detector using deep learning with an overhead depth camera

Fuentes-Jimenez

Martín-López

Losada

et al. 2020

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…Many studies have used keypoints to find the level of the crowd (number of people) due to their strong inter-dependance [55]- [58]. It is worth noting that although there is a degree of correlation relationship between the level of the crowd and the level of occlusion in a frame, this relationship is not always valid in all scenarios.…”

Section: The Occlusion-level Modelmentioning

confidence: 99%

“…The results of using moving keypoints to find the number of people show that they have a strong relationship [55]- [58]. Many people counting studies have been carried out using FAST, SIFT and SURF points [24], [60].…”

Section: Feature Representation and Selectionmentioning

confidence: 99%

An adaptive people counting system with dynamic features selection and occlusion handling

Habeeb

Ndzi

Yang

et al. 2016

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

This paper presents an adaptive crowd counting system for video surveillance applications. The proposed method is composed of a pair of collaborative Gaussian process models (GP) with different kernels, which are designed to count people by taking the level of occlusion into account. The level of occlusion is measured and compared with a predefined threshold for regression model selection for each frame. In addition, the proposed method dynamically identifies the best combination of features for people counting. The Mall and UCSD datasets are used to evaluate the proposed method. The results show that the proposed method offers a higher accuracy when compared against state of the art methods reported in open literature. The mean absolute error (MAE), mean squared error (MSE) and the mean deviation error (MDE) for the proposed algorithm are 2.90, 13.70 and 0.095, respectively, for the Mall dataset and 1.63, 4.32 and 0.066, respectively, for UCSD dataset.

show abstract

“…Local algorithms count the number of people by partitioning the frame into several regions and one local regression function is trained for each region to count the total number of people in the whole frame. The regions can be cells having regular or irregular sizes [18] or the regions can be foreground blobs and the total number of people is counted by summing the numbers in all regions [43], [65]- [68].…”

Section: Low-level Features Regression Based Algorithmsmentioning

confidence: 99%

A robust multimedia surveillance system for people counting

Habeeb

Ndzi

Kamarudin

et al. 2016

Multimed Tools Appl

View full text Add to dashboard Cite

Closed circuit television cameras (CCTV) are widely used in monitoring. This paper presents an intelligent CCTV crowd counting system based on two algorithms that estimate the density of each pixel in each frame and use it as a basis for counting people. One algorithm uses scale-invariant feature transform (SIFT) features and clustering to represent pixels of frames (SIFT algorithm) and the other uses features from accelerated segment test (FAST) corner points with SIFT features (SIFT-FAST algorithm). Each algorithm is designed using a novel combination of pixel-wise, motion-region, grid map, background segmentation using Gaussian mixture model (GMM) and edge detection. A fusion technique is proposed and used to validate the accuracy by combining the result of the algorithms at frame level. The proposed system is more practical than the state of the art regression methods because it is trained with a small number of frames so it is relatively easy to deploy. In addition, it reduces the training error, setup time, cost and open the door to develop more accurate people detection methods. The University of California (UCSD) and Mall datasets have been used to test the proposed algorithms. The mean deviation error, mean squared error and the mean absolute error of the proposed system are less than 0.1, 16.5 and 3.1, respectively, for the Mall dataset and less than 0.07, 5.5 and 1.9, respectively, for UCSD dataset.

show abstract

A method for counting moving and stationary people by interest point classification

Cited by 13 publications

References 7 publications

DPDnet: A robust people detector using deep learning with an overhead depth camera

DPDnet: A robust people detector using deep learning with an overhead depth camera

An adaptive people counting system with dynamic features selection and occlusion handling

A robust multimedia surveillance system for people counting

Contact Info

Product

Resources

About