Learning to Predict Human Behavior in Crowded Scenes

Alahi, Alexandre; Ramanathan, Vignesh; Goel, Kratarth; Robicquet, Alexandre; Sadeghian, AmirAbbas; Li, Feifei; Savarese, Silvio

doi:10.1016/b978-0-12-809276-7.00011-4

Cited by 46 publications

(36 citation statements)

References 60 publications

(94 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All these sequences are captured from a more or less aerial and oblique views. Those benchmarks have been used by many authors [ 52 , 53 , 54 , 55 , 56 , 57 , 58 ] for different purposes from tracking to human behavior prediction in crowded scenes.…”

Section: Resultsmentioning

confidence: 99%

Moving Object Detection in Heterogeneous Conditions in Embedded Systems

Garbo

Quer

2017

Sensors

View full text Add to dashboard Cite

This paper presents a system for moving object exposure, focusing on pedestrian detection, in external, unfriendly, and heterogeneous environments. The system manipulates and accurately merges information coming from subsequent video frames, making small computational efforts in each single frame. Its main characterizing feature is to combine several well-known movement detection and tracking techniques, and to orchestrate them in a smart way to obtain good results in diversified scenarios. It uses dynamically adjusted thresholds to characterize different regions of interest, and it also adopts techniques to efficiently track movements, and detect and correct false positives. Accuracy and reliability mainly depend on the overall receipt, i.e., on how the software system is designed and implemented, on how the different algorithmic phases communicate information and collaborate with each other, and on how concurrency is organized. The application is specifically designed to work with inexpensive hardware devices, such as off-the-shelf video cameras and small embedded computational units, eventually forming an intelligent urban grid. As a matter of fact, the major contribution of the paper is the presentation of a tool for real-time applications in embedded devices with finite computational (time and memory) resources. We run experimental results on several video sequences (both home-made and publicly available), showing the robustness and accuracy of the overall detection strategy. Comparisons with state-of-the-art strategies show that our application has similar tracking accuracy but much higher frame-per-second rates.

show abstract

Section: Resultsmentioning

confidence: 99%

Moving Object Detection in Heterogeneous Conditions in Embedded Systems

Garbo

Quer

2017

Sensors

View full text Add to dashboard Cite

show abstract

“…LSTM neglects to figure out how to effectively process certain ceaseless time arrangement that are not from the earlier divided into preparing subsequence with unmistakably characterized closes. LSTM comprehends complex long time slack undertakings that have never been settled by past RNN calculations [15]. Space-time model and Hidden Markov models use LSTM to detect huge number of pedestrians moving in unlike directions.…”

Section: Long Short Term Method: a Comprehensive Study I Existing Mementioning

confidence: 99%

Anomaly Detection in Crowded Scene by Pedestrians Behaviour Extraction using Long Short Term Method: A Comprehensive Study

Dey¹,

Mohammad²,

Ahmed³

et al. 2019

IJEME

View full text Add to dashboard Cite

With the expansion of worldwide security concerns and a consistently expanding requirement for successful checking of open places, i.e. air terminals, railroad stations, shopping centres, crowded sports fields, army bases or smart healthcare facilities such as daily activity monitoring and fall detection in old people's homes is increasing very rapidly. The visual occlusions and ambiguities in crowded scenes, usage of suitable method and in addition the perplexing practices and scene semantics make the investigation a challenging task. This research demonstrates comprehensive and critical analysis of crowd scene involves in object detection, tracking, feature extraction and learning from visual surveillance which helps to recognize behavioural pattern. This research refers scene understanding as scene layout, i.e. finding streets, structures, sidewalks , vehicles turning, person on foot intersection and scene status such as crowd congestion, split, merge etc. The significance of the proposed comprehensive review to create crowd administration procedures and help the development of the group or people, to maintain a strategic distance from the group calamities and guarantee general society security. Based on the observation of previous research in three aspects, i.e. review based on methods, frameworks and critical existing results analysis, this research propose a framework for anomaly detection in crowded scene using LSTM (long Short-Term Method). Proposed comprehensive review is expected to contribute significantly for the investigation of behavior pattern analysis in computer vision research domains.

show abstract

“…One part of this problem is to predict the behavior of pedestrians, which is well-studied in computer vision literature [7][8][9]. There are also several review papers on pedestrian behavior prediction [10].…”

Section: Introductionmentioning

confidence: 99%

CAEV- Deep Learning-Based Hybrid Model for the Behavior Prediction of Surrounding Vehicles Over Long-time Periods

Cai

Tai

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

Autonomous vehicles need to have the ability to predict the future behavior of surrounding vehicles, which helps with proper trajectory planning and tracking. Many behavior prediction methods have limited application because they have a very limited prediction horizon. This paper proposes a deep learning-based hybrid model for behavior prediction over long-time periods, including maneuver recognition and a behavior prediction module. In the previous module, the CNN extracts the social characteristics of the target vehicle and LSTM outputs the maneuver probability vector and forms a contextual feature vector with the social features. In the lateral module, LSTM and Attention are based on the contextual feature vector to capture multi-time step information in the behavior time window to complete the prediction of the target vehicle behavior. Real-car collection and open-source vehicle trajectory datasets were used for training and testing. The results show that the proposed algorithm could predict vehicle behavior with an accuracy of 89.73% and an average prediction time of 2.032 s, which has a high engineering application value.

show abstract

Learning to Predict Human Behavior in Crowded Scenes

Cited by 46 publications

References 60 publications

Moving Object Detection in Heterogeneous Conditions in Embedded Systems

Moving Object Detection in Heterogeneous Conditions in Embedded Systems

Anomaly Detection in Crowded Scene by Pedestrians Behaviour Extraction using Long Short Term Method: A Comprehensive Study

CAEV- Deep Learning-Based Hybrid Model for the Behavior Prediction of Surrounding Vehicles Over Long-time Periods

Contact Info

Product

Resources

About