Detection and Localization of Anomalous Motion in Video Sequences from Local Histograms of Labeled Affine Flows

Pérez-Rúa, Juan-Manuel; Basset, Antoine; Bouthémy, Patrick

doi:10.3389/fict.2017.00010

Cited by 6 publications

(4 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[13] use spatiotemporal cues and represent videos as spatio-temporal graphs with the aim of minimizing a global function. Related problems are the detection of anomalies in crowded scenes ( [27,39]), and the use of eye-fixation maps for visual saliency ( [4,20,28]).…”

Section: Related Workmentioning

confidence: 99%

CNN-based temporal detection of motion saliency in videos

Maczyta¹,

Bouthémy²,

Meur³

2019

Pattern Recognition Letters

Self Cite

View full text Add to dashboard Cite

The problem addressed in this paper appertains to the domain of motion saliency in videos. However this is a new problem since we aim to extract the temporal segments of the video where motion saliency is present. It turns out to be a frame-based classification problem. A frame will be classified as dynamically salient if it contains local motion departing from its context. Temporal motion saliency detection is relevant for applications where one needs to trigger alerts or to monitor dynamic behaviours from videos. It can also be viewed as a prerequisite before computing motion saliency maps. The proposed approach handles situations with a mobile camera. It involves two main stages consisting first in cancelling the global motion due to the camera movement, then in applying a deep learning classification framework. We have investigated two ways of implementing the first stage, based on image warping, and on residual flow respectively. Experiments on real videos demonstrate that we can obtain accurate classification in highly challenging situations.

show abstract

Section: Related Workmentioning

confidence: 99%

CNN-based temporal detection of motion saliency in videos

Maczyta¹,

Bouthémy²,

Meur³

2019

Pattern Recognition Letters

Self Cite

View full text Add to dashboard Cite

show abstract

“…In many dynamic scene analysis building blocks, accuracy of polynomial regression is important, e.g., in motion segmentation [14,15], optical flow estimation [16,17,18,19], detection of motion anomalies [20], and tracking [21]. Classical methods pose parametric motion model estimation as an inverse problem that is solved through minimization of an energy functional [22,23].…”

Section: Parametric Motion Modelsmentioning

confidence: 99%

Learning how to be robust: Deep polynomial regression

Perez-Rua,

Crivelli,

Bouthemy

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Polynomial regression is a recurrent problem with a large number of applications. In computer vision it often appears in motion analysis. Whatever the application, standard methods for regression of polynomial models tend to deliver biased results when the input data is heavily contaminated by outliers. Moreover, the problem is even harder when outliers have strong structure. Departing from problem-tailored heuristics for robust estimation of parametric models, we explore deep convolutional neural networks. Our work aims to find a generic approach for training deep regression models without the explicit need of supervised annotation. We bypass the need for a tailored loss function on the regression parameters by attaching to our model a differentiable hardwired decoder corresponding to the polynomial operation at hand. We demonstrate the value of our findings by comparing with standard robust regression methods. Furthermore, we demonstrate how to use such models for a real computer vision problem, i.e., video stabilization. The qualitative and quantitative experiments show that neural networks are able to learn robustness for general polynomial regression, with results that well overpass scores of traditional robust estimation methods.

show abstract

“…A typical example is an individual walking against a crowd. It can occur in many diverse applications, such as monitoring of urban and road traffic [RB19, BFM19], safety of public areas prone to dense crowd [PRBB17], study of cell dynamics in bio-imaging [RDJ + 17], or identification of adverse weather conditions in meteorological image sequences [PBMR00]. Motion saliency detection can be useful to trigger alarms, to focus additional processing or to allow for the detection of a specific event.…”

Section: Introductionmentioning

confidence: 99%

Trajectory Saliency Detection Using Consistency-Oriented Latent Codes From a Recurrent Auto-Encoder

Maczyta

Bouthémy

Meur

2022

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

In this paper, we are concerned with the detection of progressive dynamic saliency from video sequences. More precisely, we are interested in saliency related to motion and likely to appear progressively over time. It can be relevant to trigger alarms, to dedicate additional processing or to detect specific events. Trajectories represent the best way to support progressive dynamic saliency detection. Accordingly, we will talk about trajectory saliency. A trajectory will be qualified as salient if it deviates from normal trajectories that share a common motion pattern related to a given context. First, we need a compact while discriminative representation of trajectories. We adopt a (nearly) unsupervised learning-based approach. The latent code estimated by a recurrent auto-encoder provides the desired representation. In addition, we enforce consistency for normal (similar) trajectories through the auto-encoder loss function. The distance of the trajectory code to a prototype code accounting for normality is the means to detect salient trajectories. We validate our trajectory saliency detection method on synthetic and real trajectory datasets, and highlight the contributions of its different components. We show that our method outperforms existing methods on several scenarios drawn from the publicly available dataset of pedestrian trajectories acquired in a railway station [ARF14].

show abstract

Detection and Localization of Anomalous Motion in Video Sequences from Local Histograms of Labeled Affine Flows

Cited by 6 publications

References 75 publications

CNN-based temporal detection of motion saliency in videos

CNN-based temporal detection of motion saliency in videos

Learning how to be robust: Deep polynomial regression

Trajectory Saliency Detection Using Consistency-Oriented Latent Codes From a Recurrent Auto-Encoder

Contact Info

Product

Resources

About