Object Detection with Convolutional Neural Networks

Li, Kaidong; Ma, Wenchi; Sajid, Usman; Wu, Yunkun; Wang, Guanghui

doi:10.48550/arxiv.1912.01844

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…I N recent years, convolutional neural networks have attracted a lot of attention and been successfully applied to various computer vision problems, such as object detection [24], [29], [46], face recognition [8], depth estimation [16], [17], image classification [7], [50], image-to-image translation [44], [45], and crowd counting [34]. Crowd counting is an integral part of crowd analysis.…”

Section: Introductionmentioning

confidence: 99%

ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images

Sajid

Sajid²,

Wang

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel approach for crowd counting in low to high density scenarios in static images. Current approaches cannot handle huge crowd diversity well and thus perform poorly in extreme cases, where the crowd density in different regions of an image is either too low or too high, leading to crowd underestimation or overestimation. The proposed solution is based on the observation that detecting and handling such extreme cases in a specialized way leads to better crowd estimation. Additionally, existing methods find it hard to differentiate between the actual crowd and the cluttered background regions, resulting in further count overestimation. To address these issues, we propose a simple yet effective modular approach, where an input image is first subdivided into fixedsize patches and then fed to a four-way classification module labeling each image patch as low, medium, high-dense or nocrowd. This module also provides a count for each label, which is then analyzed via a specifically devised novel decision module to decide whether the image belongs to any of the two extreme cases (very low or very high density) or a normal case. Images, specified as high-or low-density extreme or a normal case, pass through dedicated zooming or normal patch-making blocks respectively before routing to the regressor in the form of fixed-size patches for crowd estimate. Extensive experimental evaluations demonstrate that the proposed approach outperforms the state-of-the-art methods on four benchmarks under most of the evaluation criteria.

show abstract

Section: Introductionmentioning

confidence: 99%

ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images

Sajid

Sajid²,

Wang

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…D EEP networks have been dramatically driving the progress of computer vision, bringing out a series of popular models for different vision tasks [35] [31], like image classification [3] [29], object detection [32] [15], crowd counting [25], depth estimation [10], and image translation [30]. Object detection plays an important role and serves as a prerequisite for numerous computer vision applications, such as instance segmentation, face recognition, autonomous driving, and video analysis [1], [9], [11], [12], [21].…”

Section: Introductionmentioning

confidence: 99%

Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detection

Wang

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

In the majority of object detection frameworks, the confidence of instance classification is used as the quality criterion of predicted bounding boxes, like the confidence-based ranking in nonmaximum suppression (NMS). However, the quality of bounding boxes, indicating the spatial relations, is not only correlated with the classification scores. Compared with the region proposal network (RPN) based detectors, single-shot object detectors suffer the box quality as there is a lack of pre-selection of box proposals. In this paper, we aim at single-shot object detectors and propose a location-aware anchor-based reasoning (LAAR) for the bounding boxes. LAAR takes both the location and classification confidences into consideration for the quality evaluation of bounding boxes. We introduce a novel network block to learn the relative location between the anchors and the ground truths, denoted as a localization score, which acts as a location reference during the inference stage. The proposed localization score leads to an independent regression branch and calibrates the bounding box quality by scoring the predicted localization score so that the best-qualified bounding boxes can be picked up in NMS. Experiments on MS COCO and PASCAL VOC benchmarks demonstrate that the proposed location-aware framework enhances the performances of current anchor-based single-shot object detection frameworks and yields consistent and robust detection results.

show abstract

“…Deep learning has achieved significant progress in many computer vision applications, like image classification [9,3], object detection [22,18], face recognition [4], depth estimation [12,13], image translation [40,39], and crowd counting [27]. Crowd counting plays a vital role in crowd analysis applications such as better management of political rallies or sports events, traffic control, safety and security, and avoiding any political point-scoring on crowd numbers [43].…”

Section: Introductionmentioning

confidence: 99%

Plug-and-Play Rescaling Based Crowd Counting in Static Images

Sajid¹,

Wang²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Crowd counting is a challenging problem especially in the presence of huge crowd diversity across images and complex cluttered crowd-like background regions, where most previous approaches do not generalize well and consequently produce either huge crowd underestimation or overestimation. To address these challenges, we propose a new image patch rescaling module (PRM) and three independent PRM employed crowd counting methods. The proposed frameworks use the PRM module to rescale the image regions (patches) that require special treatment, whereas the classification process helps in recognizing and discarding any cluttered crowd-like background regions which may result in overestimation. Experiments on three standard benchmarks and cross-dataset evaluation show that our approach outperforms the state-of-the-art models in the RMSE evaluation metric with an improvement up to 10.4%, and possesses superior generalization ability to new datasets.

show abstract

Object Detection with Convolutional Neural Networks

Cited by 3 publications

References 0 publications

ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images

ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images

Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detection

Plug-and-Play Rescaling Based Crowd Counting in Static Images

Contact Info

Product

Resources

About