Active learning for high-density crowd count regression

Vandoni, Jennifer; Aldea, Emanuel; Hégarat‐Mascle, Sylvie Le

doi:10.1109/avss.2017.8078508

Cited by 6 publications

(4 citation statements)

References 20 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the major issues on object coverage detection is to find the coverage proportion of each object within the image. The object count [120,121] method has been applied as an approach to find the density or proportion of object area within an image. However, the object count approach for small objects appearing in a group has been a limiting factor for object count analysis [122].…”

Section: Image Annotation and Coverage Levelmentioning

confidence: 99%

Explainable Artificial Intelligence for Developing Smart Cities Solutions

et al. 2020

View full text Add to dashboard Cite

Traditional Artificial Intelligence (AI) technologies used in developing smart cities solutions, Machine Learning (ML) and recently Deep Learning (DL), rely more on utilising best representative training datasets and features engineering and less on the available domain expertise. We argue that such an approach to solution development makes the outcome of solutions less explainable, i.e., it is often not possible to explain the results of the model. There is a growing concern among policymakers in cities with this lack of explainability of AI solutions, and this is considered a major hindrance in the wider acceptability and trust in such AI-based solutions. In this work, we survey the concept of ‘explainable deep learning’ as a subset of the ‘explainable AI’ problem and propose a new solution using Semantic Web technologies, demonstrated with a smart cities flood monitoring application in the context of a European Commission-funded project. Monitoring of gullies and drainage in crucial geographical areas susceptible to flooding issues is an important aspect of any flood monitoring solution. Typical solutions for this problem involve the use of cameras to capture images showing the affected areas in real-time with different objects such as leaves, plastic bottles etc., and building a DL-based classifier to detect such objects and classify blockages based on the presence and coverage of these objects in the images. In this work, we uniquely propose an Explainable AI solution using DL and Semantic Web technologies to build a hybrid classifier. In this hybrid classifier, the DL component detects object presence and coverage level and semantic rules designed with close consultation with experts carry out the classification. By using the expert knowledge in the flooding context, our hybrid classifier provides the flexibility on categorising the image using objects and their coverage relationships. The experimental results demonstrated with a real-world use case showed that this hybrid approach of image classification has on average 11% improvement (F-Measure) in image classification performance compared to DL-only classifier. It also has the distinct advantage of integrating experts’ knowledge on defining the decision-making rules to represent the complex circumstances and using such knowledge to explain the results.

show abstract

Section: Image Annotation and Coverage Levelmentioning

confidence: 99%

Explainable Artificial Intelligence for Developing Smart Cities Solutions

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Finally, a L2 loss function is used between the estimated density map and the ground-truth derived by placing a Gaussian on each head center as in [2]. Since we know the geometry of the scene, we apply perspective correction as in [9] instead of geometry-adaptive kernels. Building a CNN-ensemble.…”

Section: Evidential Cnn-ensemblementioning

confidence: 99%

Evaluating Crowd Density Estimators Via Their Uncertainty Bounds

Vandoni

Aldea

Hégarat‐Mascle

2019

2019 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

In this work, we use the Belief Function Theory which extends the probabilistic framework in order to provide uncertainty bounds to different categories of crowd density estimators. Our method allows us to compare the multi-scale performance of the estimators, and also to characterize their reliability for crowd monitoring applications requiring varying degrees of prudence. Layers -part 1 FE Conv 3 × 3, F = 16, D = 1 Conv 3 × 3, F = 32, D = 1 Conv 3 × 3, F = 32, D = 2 Conv 3 × 3, F = 64, D = 2 Conv 3 × 3, F = 64, D = 3 Layers -part 2 LFE Conv 3 × 3, F = 64, D = 2 Conv 3 × 3, F = 64, D = 2 Conv 3 × 3, F = 64, D = 1 Conv 3 × 3, F = 64, D = 1 Conv 1 × 1, F = 1, D = 1

show abstract

“…Xiong et al [25] proposed a variant of a recent deep learning model called convolutional LSTM (ConvLSTM) for crowd counting, which fully captures both spatial and temporal dependencies. Vandoni et al [26] proposed a learning-to-count strategy with a generic detection algorithm which benefits from a counting regressor in order to identify crowded subregions with inadequate head detection performance. The experiment results showed the effectiveness with a count error of less than 5%.…”

Section: Crowdedness Estimationmentioning

confidence: 99%

BCE: A Behavior-Learning-Based Crowdedness Estimation Mechanism for Crowdsensing Buses

Niu

Zhang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

This paper aims to develop a method that can accurately estimate the crowdedness level for crowdsensing buses. Multiple related features are reflected by passengers' moving trajectories at the bus stops. Many state-of-the-art posture recognition approaches have high accuracy, which can ensure that the passengers motion monitoring results are reliable. Through these observations, we propose an improved behavior-learning-based crowdedness estimation mechanism, named BCE, to obtain the crowdedness level of a bus. The motion sequence and gait information of a passenger is obtained via sensors in smartphones and is described by feature vectors. Then the feature vectors are classified as bus crowdedness levels based on gcForest classifier for single-person bus's crowdedness level estimation and on Recurrent Neural Network (RNN) for multipeople bus's crowdedness level estimation. Additionally, the moving trajectories and the corresponding crowdedness of the passengers who do not involve in our system can be recognized passively through the motion information of adjacent involved passengers on the bus. The experiments prove that our mechanism achieves an accuracy of 92% overall.

show abstract

Active learning for high-density crowd count regression

Cited by 6 publications

References 20 publications

Explainable Artificial Intelligence for Developing Smart Cities Solutions

Explainable Artificial Intelligence for Developing Smart Cities Solutions

Evaluating Crowd Density Estimators Via Their Uncertainty Bounds

BCE: A Behavior-Learning-Based Crowdedness Estimation Mechanism for Crowdsensing Buses

Contact Info

Product

Resources

About