Disam: Density Independent and Scale Aware Model for Crowd Counting and Localization

Khan, Sultan Daud; Ullah, Habib; Uzair, Mohammad; Ullah, Mohib; Ullah, Rehan; Cheikh, Faouzi Alaya

doi:10.1109/icip.2019.8803409

Cited by 27 publications

(22 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, since motion information is not included when training the model presented in [25], if an object that is tracked is moving in one direction and it gets partially occluded by a similar object moving in the opposing direction, there is a chance that the tracker will latch onto the wrong object. In [26], the authors propose a neural network model that can localize the exact position of people in a scene. With this information, people can be detected and tracked in dense environments.…”

Section: Multi-target Tracking and Data Associationmentioning

confidence: 99%

See 1 more Smart Citation

Stabilization and Validation of 3D Object Position Using Multimodal Sensor Fusion and Semantic Segmentation

Muresan

Giosan

Nedevschi

2020

Sensors

View full text Add to dashboard Cite

The stabilization and validation process of the measured position of objects is an important step for high-level perception functions and for the correct processing of sensory data. The goal of this process is to detect and handle inconsistencies between different sensor measurements, which result from the perception system. The aggregation of the detections from different sensors consists in the combination of the sensorial data in one common reference frame for each identified object, leading to the creation of a super-sensor. The result of the data aggregation may end up with errors such as false detections, misplaced object cuboids or an incorrect number of objects in the scene. The stabilization and validation process is focused on mitigating these problems. The current paper proposes four contributions for solving the stabilization and validation task, for autonomous vehicles, using the following sensors: trifocal camera, fisheye camera, long-range RADAR (Radio detection and ranging), and 4-layer and 16-layer LIDARs (Light Detection and Ranging). We propose two original data association methods used in the sensor fusion and tracking processes. The first data association algorithm is created for tracking LIDAR objects and combines multiple appearance and motion features in order to exploit the available information for road objects. The second novel data association algorithm is designed for trifocal camera objects and has the objective of finding measurement correspondences to sensor fused objects such that the super-sensor data are enriched by adding the semantic class information. The implemented trifocal object association solution uses a novel polar association scheme combined with a decision tree to find the best hypothesis–measurement correlations. Another contribution we propose for stabilizing object position and unpredictable behavior of road objects, provided by multiple types of complementary sensors, is the use of a fusion approach based on the Unscented Kalman Filter and a single-layer perceptron. The last novel contribution is related to the validation of the 3D object position, which is solved using a fuzzy logic technique combined with a semantic segmentation image. The proposed algorithms have a real-time performance, achieving a cumulative running time of 90 ms, and have been evaluated using ground truth data extracted from a high-precision GPS (global positioning system) with 2 cm accuracy, obtaining an average error of 0.8 m.

show abstract

Section: Multi-target Tracking and Data Associationmentioning

confidence: 99%

“…The rest of the points are generated with a spreading factor of λ around the mean, as depicted in (26) and (27).…”

Section: The Unscented Kalman Filter and Sensor Fusionmentioning

confidence: 99%

Stabilization and Validation of 3D Object Position Using Multimodal Sensor Fusion and Semantic Segmentation

Muresan

Giosan

Nedevschi

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…For WIDERFACE dataset, we use different group of face detectors that includes CMS-RCNN [58], Multitask-CNN [55], ACF [48], and TinyFace [13]. While head detector group includes, DPM-Head [52], DHD [35], FCHD [44] and DISAM [17].…”

Section: B Comparison With Specific Head Detectorsmentioning

confidence: 99%

“…Due to small size of head, DPM detector could not detect the heads with the size less than 23 × 23 pixels. DISAM [17], on the other hand achieved comparable results by tackling scale problem to some extent, however the method suffers from the following limitations: (1) The models follows the traditional pipeline of R-CNN which uses scale-aware strategy for object proposal generation. The strategy typically requires human efforts to generate a scale map.…”

Section: B Comparison With Specific Head Detectorsmentioning

confidence: 99%

Robust Head Detection in Complex Videos Using Two-Stage Deep Convolution Framework

Khan

Ali²,

Zafar³

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Pedestrian head detection plays an important role in identifying and localizing individuals in real world visual data. Head detection is a nontrivial problem due to considerable variance in camera viewpoints, scales, human poses, and appearances in the scene. Thanks to the translation invariance property of convolutional neural networks (CNNs) which enables large capacity CNNs to handle the problem of appearance and pose variations in the scene. However, the problem of scale invariance is still an open issue. To address this problem, this paper presents a two-stage head detection framework that utilizes fully convolutional network (FCN) to generate scale-aware proposals followed by CNN that classifies each proposal into two classes, i.e. head and background. Experiments results show that using scale-aware proposals obtained by FCN, the object recall rate and mean average precision (mAP) are improved. Additionaly, we demonstrate that our framework achieved state-of-the-art results on four challenging benchmark datasets, i.e. HollywoodHeads, Casablanca, SHOCK, and WIDERFACE.

show abstract

“…Serious games are also called applied games and this concept of gaming is used by industries like defense [3], health care [4], emergency management [5], [6], education [7], exploration [8], city planning [9], engineering [10], and politics [11]. In addition to this, computer vision and deep learning based techniques can be exploited in gaming context to analyze performances of sports players through tracking [12], [13] in an virtual environment [14], detection [15], [16], analysing anomalous behaviour [17], [18], simulating individual [19], [20] and crowd behaviour [21]- [25] for public infrastructure design [26], [27], and a variety of other multi media applications [28], [29]. Fig.…”

Section: Introductionmentioning

confidence: 99%

Serious Games and Gamification: A Systematic Literature Review

Khan¹,

Khan²,

Safaev³

2020

Preprint

View full text Add to dashboard Cite

Keeping in mind the increasing trend and need for serious games in science education, we have done a systematic literature review. These papers show the trends and patterns of research carried out in this field from the year 2011 to 2020. Specifically, we investigated country-wise concentration and the most common evaluation methods. Literature is reviewed from IEEEexplore, Springer, and Scopus. Moreover, we discussed the role of Augmented Reality(AR) games in teaching physics. Lastly, we have discussed the positive and negative aspects of serious games in science education in particular, and the trend of using serious games in the past decade in education in general.

show abstract

Disam: Density Independent and Scale Aware Model for Crowd Counting and Localization

Cited by 27 publications

References 17 publications

Stabilization and Validation of 3D Object Position Using Multimodal Sensor Fusion and Semantic Segmentation

Stabilization and Validation of 3D Object Position Using Multimodal Sensor Fusion and Semantic Segmentation

Robust Head Detection in Complex Videos Using Two-Stage Deep Convolution Framework

Serious Games and Gamification: A Systematic Literature Review

Contact Info

Product

Resources

About