+1 Recommend
0 collections
      • Record: found
      • Abstract: found
      • Article: not found

      Revisiting crowd behaviour analysis through deep learning: Taxonomy, anomaly detection, crowd emotions, datasets, opportunities and prospects


      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.


          Crowd behaviour analysis is an emerging research area. Due to its novelty, a proper taxonomy to organise its different sub-tasks is still missing. This paper proposes a taxonomic organisation of existing works following a pipeline, where sub-problems in last stages benefit from the results in previous ones. Models that employ Deep Learning to solve crowd anomaly detection, one of the proposed stages, are reviewed in depth, and the few works that address emotional aspects of crowds are outlined. The importance of bringing emotional aspects into the study of crowd behaviour is remarked, together with the necessity of producing real-world, challenging datasets in order to improve the current solutions. Opportunities for fusing these models into already functioning video analytics systems are proposed.


          • Proposal of hierarchical taxonomy for crowd behaviour analysis subtasks.

          • Review and numeric comparison of Deep Learning models for crowd anomaly detection.

          • Discussion of current limitations in datasets and importance of going beyond.

          • Discussion of the importance of using emotional aspects in crowd behaviour analysis.

          • Proposals of fusion crowd analysis models into existing video analytics solutions.

          Related collections

          Most cited references51

          • Record: found
          • Abstract: found
          • Article: not found

          Facial expression megamix: tests of dimensional and category accounts of emotion recognition.

          We report four experiments investigating the perception of photographic quality continua of interpolated ('morphed') facial expressions derived from prototypes of the 6 emotions in the Ekman and Friesen (1976) series (happiness, surprise, fear, sadness, disgust and anger). In Experiment 1, morphed images made from all possible pairwise combinations of expressions were presented in random order; subjects identified these as belonging to distinct expression categories corresponding to the prototypes at each end of the relevant continuum. This result was replicated in Experiment 2, which also included morphs made from a prototype with a neutral expression, and allowed 'neutral' as a response category. These findings are inconsistent with the view that facial expressions are recognised by locating them along two underlying dimensions, since such a view predicts that at least some transitions between categories should involve neutral regions or identification as a different emotion. Instead, they suggest that facial expressions of basic emotions are recognised by their fit to discrete categories. Experiment 3 used continua involving 6 emotions to demonstrate best discrimination of pairs of stimuli falling across category boundaries; this provides further evidence of categorical perception of facial expressions of emotion. However, in both Experiment 1 and Experiment 2, reaction time data showed that increasing distance from the prototype had a definite cost on ability to identify emotion in the resulting morphed face. Moreover, Experiment 4 showed that subjects had some insight into which emotions were blended to create specific morphed images. Hence, categorical perception effects were found even though subjects were sensitive to physical properties of these morphed facial expressions. We suggest that rapid classification of prototypes and better across boundary discriminability reflect the underlying organisation of human categorisation abilities.
            • Record: found
            • Abstract: found
            • Article: not found

            PCANet: A Simple Deep Learning Baseline for Image Classification?

            In this paper, we propose a very simple deep learning network for image classification that is based on very basic data processing components: 1) cascaded principal component analysis (PCA); 2) binary hashing; and 3) blockwise histograms. In the proposed architecture, the PCA is employed to learn multistage filter banks. This is followed by simple binary hashing and block histograms for indexing and pooling. This architecture is thus called the PCA network (PCANet) and can be extremely easily and efficiently designed and learned. For comparison and to provide a better understanding, we also introduce and study two simple variations of PCANet: 1) RandNet and 2) LDANet. They share the same topology as PCANet, but their cascaded filters are either randomly selected or learned from linear discriminant analysis. We have extensively tested these basic networks on many benchmark visual data sets for different tasks, including Labeled Faces in the Wild (LFW) for face verification; the MultiPIE, Extended Yale B, AR, Facial Recognition Technology (FERET) data sets for face recognition; and MNIST for hand-written digit recognition. Surprisingly, for all tasks, such a seemingly naive PCANet model is on par with the state-of-the-art features either prefixed, highly hand-crafted, or carefully learned [by deep neural networks (DNNs)]. Even more surprisingly, the model sets new records for many classification tasks on the Extended Yale B, AR, and FERET data sets and on MNIST variations. Additional experiments on other public data sets also demonstrate the potential of PCANet to serve as a simple but highly competitive baseline for texture classification and object recognition.
              • Record: found
              • Abstract: not found
              • Article: not found

              Towards a Theory of Collective Emotions


                Author and article information

                Inf Fusion
                Inf Fusion
                An International Journal on Information Fusion
                Published by Elsevier B.V.
                29 July 2020
                29 July 2020
                [a ]Andalusian Research Institute in Data Science and Computational Intelligence, University of Granada, Granada, Spain
                [b ]Herta Security, Barcelona, Spain
                Author notes
                [* ]Corresponding author. fluque@ 123456decsai.ugr.es
                © 2020 Published by Elsevier B.V.

                Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.

                : 8 June 2020
                : 20 July 2020
                : 21 July 2020

                crowd behaviour analysis,crowd anomaly detection,crowd emotions,review,deep learning,models fusion


                Comment on this article