Depth Information Guided Crowd Counting for complex crowd scenes

Xu, Mingliang; Ge, Zhaoyang; Jiang, Xiaoheng; Cui, Gaoge; Lv, Pei; Zhou, Bing; Xu, Changsheng

doi:10.1016/j.patrec.2019.02.026

Cited by 55 publications

(19 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a Gated U-Net (GU-Net) was employed to determine the amount of information passed to the final layer (convolution or fully connected) for a more accurate feature-selection process. Similar to the idea of [109], Xu et al [111] proposed a depth-of-information-based guided crowd-counting method (Digcrowd) to deal with highly dense and varying-perspective images. Segmentation was performed on an image to divide it into two regions: farand near-view regions.…”

Section: Patch-based-cnn-cc Techniquesmentioning

confidence: 99%

“…This is due to the consideration of density-level classification of image patches with a density-oriented-based regressor approach. Further, the nMAE of [115] was relatively low when compared to that of [110][111][112]114,116] on the STA dataset. This is due to consideration of a skip connection with scale-oriented training to handle varying-scale issues.…”

mentioning

confidence: 96%

“…Refs. [109][110][111][112][113][114][115][116] as Patch-based-CNN-CC algorithms tested via the UCF, STA and STB datasets. •…”

mentioning

confidence: 99%

See 2 more Smart Citations

Convolutional-Neural Network-Based Image Crowd Counting: Review, Categorization, Analysis, and Performance Evaluation

Ilyas

Shahzad

Kim

2019

Sensors

View full text Add to dashboard Cite

Traditional handcrafted crowd-counting techniques in an image are currently transformed via machine-learning and artificial-intelligence techniques into intelligent crowd-counting techniques. This paradigm shift offers many advanced features in terms of adaptive monitoring and the control of dynamic crowd gatherings. Adaptive monitoring, identification/recognition, and the management of diverse crowd gatherings can improve many crowd-management-related tasks in terms of efficiency, capacity, reliability, and safety. Despite many challenges, such as occlusion, clutter, and irregular object distribution and nonuniform object scale, convolutional neural networks are a promising technology for intelligent image crowd counting and analysis. In this article, we review, categorize, analyze (limitations and distinctive features), and provide a detailed performance evaluation of the latest convolutional-neural-network-based crowd-counting techniques. We also highlight the potential applications of convolutional-neural-network-based crowd-counting techniques. Finally, we conclude this article by presenting our key observations, providing strong foundation for future research directions while designing convolutional-neural-network-based crowd-counting techniques. Further, the article discusses new advancements toward understanding crowd counting in smart cities using the Internet of Things (IoT).

show abstract

Section: Patch-based-cnn-cc Techniquesmentioning

confidence: 99%

mentioning

confidence: 96%

See 1 more Smart Citation

Convolutional-Neural Network-Based Image Crowd Counting: Review, Categorization, Analysis, and Performance Evaluation

Ilyas

Shahzad

Kim

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…In fact, automated crowd investigation plays an crucial role in crowd analysis and visual surveillance videos considering these CCTV cameras and other installation systems [11] [12]. Therefore, in terms of designing public spaces, visual surveillance systems, and intelligent controlled physical situations [13]. Therese kind of approaches will have various important applications such as the monitoring of crowd flows, taking care of accidents, and managing evacuation designs required in the bad event of a sudden and uncontrolled fire or in presence of riots in cities zones especially [14][15] [16].…”

Section: Introductionmentioning

confidence: 99%

Challenges of Deep Learning for Crowd Analytics

Siraj¹

2019

Preprint

View full text Add to dashboard Cite

In high population cities, the gatherings of large crowds in public places and public areas accelerate or jeopardize people safety and transportation, which is a key challenge to the researchers. Although much research has been carried out on crowd analytics, many of existing methods are problem-specific, i.e., methods learned from a specific scene cannot be properly adopted to other videos. Therefore, this presents weakness and the discovery of these researches, since additional training samples have to be found from diverse videos. This paper will investigate diverse scene crowd analytics with traditional and deep learning models. We will also consider pros and cons of these approaches. However, once general deep methods are investigated from large datasets, they can be consider to investigate different crowd videos and images. Therefore, it would be able to cope with the problem including to not limited to crowd density estimation, crowd people counting, and crowd event recognition. Deep learning models and approaches are required to have large datasets for training and testing. Many datasets are collected taking into account many different and various problems related to building crowd datasets, including manual annotations and increasing diversity of videos and images. In this paper, we will also propose many models of deep neural networks and training approaches to learn the feature modeling for crowd analytics.

show abstract

“…For this purpose, they combine local low-level cues [6] [7] [8], global features [9] [10], visual organization rules [11], and high-level factors [12] [13]. Xie et al [14] consider local low-level features [15] and mid-level cues [16] [17] within the Bayesian framework to detect saliency. Wang et al [18] propose a bottom-up visual saliency detection algorithm.…”

Section: Introductionmentioning

confidence: 99%

A Unified Model for Salient Object Detection

Alzahrani¹,

Afridi²

2019

Preprint

View full text Add to dashboard Cite

We propose a novel method for salient object detection in different images. Our method integrates spatial features for efficient and robust representation to capture meaningful information about the salient objects. We then train a conditional random field (CRF) using the integrated features. The trained CRF model is then used to detect salient objects during the online testing stage. We perform experiments on two standard datasets and compare the performance of our method with different reference methods. Our experiments show that our method outperforms the compared methods in terms of precision, recall, and F-Measure.

show abstract

Depth Information Guided Crowd Counting for complex crowd scenes

Cited by 55 publications

References 22 publications

Convolutional-Neural Network-Based Image Crowd Counting: Review, Categorization, Analysis, and Performance Evaluation

Convolutional-Neural Network-Based Image Crowd Counting: Review, Categorization, Analysis, and Performance Evaluation

Challenges of Deep Learning for Crowd Analytics

A Unified Model for Salient Object Detection

Contact Info

Product

Resources

About