Segmentation of crowd flow by trajectory clustering in active contours

Lamba, Sonu; Nain, Neeta

doi:10.1007/s00371-019-01713-7

Cited by 6 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While numerous works have been done on motion patternbased crowd analysis [3,12,[17][18][19][20], only a few of them focus on classifying a scene into the aforementioned three categories (structured, semi-structured, and unstructured). Among them, Zhou et al [16,21] introduced a descriptor to quantify a crowded scene based on its 'collectiveness', which is defined as "the degree of individuals acting as a union in collective motion".…”

Section: Related Workmentioning

confidence: 99%

Motion pattern-based crowd scene classification using histogram of angular deviations of trajectories

et al. 2022

View full text Add to dashboard Cite

Automated crowd behaviour analysis and monitoring is a challenging task due to the unpredictable nature of the crowd within a particular scene and across different scenes. The prior knowledge of the type of scene under consideration is a crucial mid-level information, which could be utilized to develop robust crowd behaviour analysis systems. In this paper, we propose an approach to automatically detect the type of a crowded scene based on the global motion patterns of the objects within the scene. Three different types of scenes whose global motion pattern characteristics vary from uniform to non-uniform are considered in this work, namely structured, semi-structured, and unstructured scenes, respectively. To capture the global motion pattern characteristics of an input crowd scene, we first extract the motion information in the form of trajectories using a key-point tracker and then compute the average angular orientation feature of each trajectory. This paper utilizes these angular features to introduce a novel feature vector, termed as Histogram of Angular Deviations (HAD), which depicts the distribution of the pair-wise angular deviation values for each trajectory vector. Since angular deviation information is resistant to changes in scene perspectives, we consider it as a key feature for distinguishing the scene types. To evaluate the effectiveness of the proposed HAD-based feature vector in classifying the crowded scenes, we build a crowd scene classification model by training the classical machine learning algorithms on the publicly available Collective Motion Database. The experimental results demonstrate the superior crowd classification performance of the proposed approach as compared to the existing methods. In addition to this, we propose a technique based on quantizing the angular deviation values to reduce the feature dimension and subsequently introduce a novel crowd scene structuredness index to quantify the structuredness of an input crowded scene based on its HAD.

show abstract

Section: Related Workmentioning

confidence: 99%

Motion pattern-based crowd scene classification using histogram of angular deviations of trajectories

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Face tracking has become a feature of many face-based emotion-recognition systems and many tools, including measurement of optical flow [28]. In addition to active contour models [29], face identification, recovery of a facial pose following facial expression [30], probabilistic approaches to detecting and tracking human faces [31], active [32] and adaptive [33] appearance models, multiple Eigenspaces-based methods [34], robust appearance filters [35], and facial motion extraction based on optical flow [36], there are several other methods. Thus, the deep learning framework clarifies many classifiers used in several tasks of facial expression recognition.…”

Section: Face Emotion Recognitionmentioning

confidence: 99%

Facial Recognition System to Detect Student Emotions and Cheating in Distance Learning

et al. 2022

View full text Add to dashboard Cite

Distance learning has spread nowadays on a large scale across the world, which has led to many challenges in education such as invigilation and learning coordination. These challenges have attracted the attention of many researchers aiming at providing high quality and credibility monitoring of students. Distance learning has offered an effective education alternative to traditional learning in higher education. The lecturers in universities face difficulties in understanding students’ emotions and abnormal behaviors during educational sessions and e-exams. The purpose of this study is to use computer vision algorithms and deep learning algorithms to develop a new system that supports lecturers in monitoring and managing students during online learning sessions and e-exams. To achieve the proposed objective, the system employs software methods, computer vision algorithms, and deep learning algorithms. Semi-structural interviews were also used as feedback to enhance the system. The findings showed that the system achieved high accuracy for student identification in real time, student follow-up during the online session, and cheating detection. Future work can focus on developing additional tools to assist students with special needs and speech recognition to improve the follow-up facial recognition system’s ability to detect cheating during e-exams in distance learning.

show abstract

AMNet: a new RGB-D instance segmentation network based on attention and multi-modality

Wang

Bai

et al. 2023

Vis Comput

View full text Add to dashboard Cite

Segmentation of crowd flow by trajectory clustering in active contours

Cited by 6 publications

References 36 publications

Motion pattern-based crowd scene classification using histogram of angular deviations of trajectories

Motion pattern-based crowd scene classification using histogram of angular deviations of trajectories

Facial Recognition System to Detect Student Emotions and Cheating in Distance Learning

AMNet: a new RGB-D instance segmentation network based on attention and multi-modality

Contact Info

Product

Resources

About