PIDNet: An Efficient Network for Dynamic Pedestrian Intrusion Detection

Sun, Jingchen; Chen, Jiming; Chen, Tao; Fan, Jianchao; He, Shibo

doi:10.1145/3394171.3413837

Cited by 9 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pedestrian trajectory forecasting deals with predicting future paths through the exploitation of individual trajectory information and mutual influence between pedestrians. This task has several practical applications in advanced surveillance systems [24], behavioral analysis [32], intrusion detection [39], smart vehicles and autonomous systems [4,37].…”

Section: Introductionmentioning

confidence: 99%

How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting

Monti

Porrello

Calderara

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Accurate prediction of future human positions is an essential task for modern video-surveillance systems. Current state-of-the-art models usually rely on a "history" of past tracked locations (e.g., 3 to 5 seconds) to predict a plausible sequence of future locations (e.g., up to the next 5 seconds). We feel that this common schema neglects critical traits of realistic applications: as the collection of input trajectories involves machine perception (i.e., detection and tracking), incorrect detection and fragmentation errors may accumulate in crowded scenes, leading to tracking drifts. On this account, the model would be fed with corrupted and noisy input data, thus fatally affecting its prediction performance.In this regard, we focus on delivering accurate predictions when only few input observations are used, thus potentially lowering the risks associated with automatic perception. To this end, we conceive a novel distillation strategy that allows a knowledge transfer from a teacher network to a student one, the latter fed with fewer observations (just two ones). We show that a properly defined teacher supervision allows a student network to perform comparably to state-of-the-art approaches that demand more observations. Besides, extensive experiments on common trajectory forecasting datasets highlight that our student network better generalizes to unseen scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting

Monti

Porrello

Calderara

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Pedestrian trajectory forecasting deals with predicting future paths through the exploitation of individual trajectory information and mutual influence between pedestrians. This task has several practical applications in advanced surveillance systems [23], behavioral analysis [31], intrusion detection [38], smart vehicles and autonomous systems [4,36].…”

Section: Introductionmentioning

confidence: 99%

How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting

Monti¹,

Porrello²,

Calderara³

et al. 2022

Preprint

View full text Add to dashboard Cite

Accurate prediction of future human positions is an essential task for modern video-surveillance systems. Current state-of-the-art models usually rely on a "history" of past tracked locations (e.g., 3 to 5 seconds) to predict a plausible sequence of future locations (e.g. up to the next 5 seconds). We feel that this common schema neglects critical traits of realistic applications: as the collection of input trajectories involves machine perception (i.e., detection and tracking), incorrect detection and fragmentation errors may accumulate in crowded scenes, leading to tracking drifts. On this account, the model would be fed with corrupted and noisy input data, thus fatally affecting its prediction performance.In this regard, we focus on delivering accurate predictions when only few input observations are used, thus potentially lowering the risks associated with automatic perception. To this end, we conceive a novel distillation strategy that allows a knowledge transfer from a teacher network to a student one, the latter fed with fewer observations (just two ones). We show that a properly defined teacher supervision allows a student network to perform comparably to state-of-the-art approaches that demand more observations. Besides, extensive experiments on common trajectory forecasting datasets highlight that our student network better generalizes to unseen scenarios.

show abstract

Research on Pedestrian Intrusion Detection Method in Coal Mine Based on Deep Learning

Yuan,

Liu

2024

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

PIDNet: An Efficient Network for Dynamic Pedestrian Intrusion Detection

Cited by 9 publications

References 37 publications

How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting

How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting

How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting

Research on Pedestrian Intrusion Detection Method in Coal Mine Based on Deep Learning

Contact Info

Product

Resources

About