Vision‐based garbage dumping action detection for real‐world surveillance platform

Yun, Kimin; Kwon, Yongjin; Oh, Sungchan; Moon, Jinyoung; Park, Jongyoul

doi:10.4218/etrij.2018-0520

Cited by 47 publications

(20 citation statements)

References 44 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The experimental results verify the superior performance of the proposed method over existing state-of-the-art methods [20], [21]. Further, we also demonstrate qualitatively the improved results of the proposed method on several datasets [25]- [27] that contain images of people in reclining postures because of the angle of the pre-installed camera.…”

Section: Introductionsupporting

confidence: 67%

“…Figures 14 and 15 qualitatively visualize the human pose estimation results of the baseline method (HRNet-W32 trained on COCO dataset) and the proposed method on the surveillance action dataset [25], [26]. Figure 14 presents the results of human pose estimation in the case in which the image is rotated according to the evaluation protocol on the garbage dumping action dataset [25], [33]: The columns records the results for the image rotated by 60, 120, 180, and 270 degrees. As depicted in Figure 14, rotational robustness is improved on the actual surveillance dataset as well as the MPII and COCO datasets used in the quantitative evaluation.…”

Section: Qualitative Resultsmentioning

confidence: 99%

“…• Based on a real-world surveillance dataset [25], [33], ICVL dataset [26], and IASLAB Fallen Person dataset [27], we present qualitative results to verify the robustness of the proposed network against rotation (Section V-D).…”

Section: Methodsmentioning

confidence: 99%

“…Examples of results of the conventional human pose estimation and the proposed human pose estimation on a real-world surveillance dataset[25],[33].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Robust Human Pose Estimation for Rotation via Self-Supervised Learning

2020

Self Cite

View full text Add to dashboard Cite

The detection of abnormal postures, such as that of a reclining person, is a crucial part of visual surveillance. Further, even regular poses can appear rotated because of incongruity between the image and the angle of a pre-installed camera. However, most existing human pose estimation methods focus on small rotational changes, i.e., those less than 50 degrees, and they seldom consider robust human pose estimation for more drastic rotational changes. To the best of our knowledge, there have been no reports on the robustness of human pose estimation for rotational changes through large angles. In this study, we propose a robust human pose estimation method by creating a path for learning new rotational changes based on a self-supervised method and by combining the results with those obtained from a path based on a supervised method. Furthermore, a combination module composed of a convolutional layer is trained complementarily by both paths of the network to produce robust results for various rotational changes. We demonstrate the robustness of the proposed method with extensive experiments on images generated by rotating the elements of standard benchmark datasets. We fully analyze the rotational characteristics of the state-of-the-art human pose estimators and the proposed method. On the COCO Keypoint Detection dataset, the proposed method attains more than 15% improvement in the mean of average precision compared to the state-of-the-art method, and the standard deviation of the performance is improved by more than 4.7 times.

show abstract

Section: Introductionsupporting

confidence: 67%

Section: Qualitative Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…Examples of results of the conventional human pose estimation and the proposed human pose estimation on a real-world surveillance dataset[25],[33].…”

mentioning

confidence: 99%

See 2 more Smart Citations

Robust Human Pose Estimation for Rotation via Self-Supervised Learning

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Human–object interaction (HOI) detection aims to detect human and object locations and classify their interactions at the instance level (eg, a person riding a bike, carrying a backpack, and throwing a frisbee), which can be formulated as detecting a triplet (human, action, and object) . This task is beneficial to many applications that require a deeper understanding of semantic scenes, such as video surveillance and visual question answering .…”

Section: Introductionmentioning

confidence: 99%

Three‐stream network with context convolution module for human–object interaction detection

2020

View full text Add to dashboard Cite

Human–object interaction (HOI) detection is a popular computer vision task that detects interactions between humans and objects. This task can be useful in many applications that require a deeper understanding of semantic scenes. Current HOI detection networks typically consist of a feature extractor followed by detection layers comprising small filters (eg, 1 × 1 or 3 × 3). Although small filters can capture local spatial features with a few parameters, they fail to capture larger context information relevant for recognizing interactions between humans and distant objects owing to their small receptive regions. Hence, we herein propose a three‐stream HOI detection network that employs a context convolution module (CCM) in each stream branch. The CCM can capture larger contexts from input feature maps by adopting combinations of large separable convolution layers and residual‐based convolution layers without increasing the number of parameters by using fewer large separable filters. We evaluate our HOI detection method using two benchmark datasets, V‐COCO and HICO‐DET, and demonstrate its state‐of‐the‐art performance.

show abstract

Efficient solid waste inspection through drone‐based aerial imagery and TinyML vision model

Malche,

Maheshwary,

Tiwari

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Solid waste management is a significant challenge in the development of smart cities. Existing approaches for solid waste monitoring are often time‐consuming and resource intensive. Therefore, this study proposes a novel approach to solid waste monitoring that utilizes drone technology. The proposed method enables the efficient identification and classification of waste objects in the garbage discovered by the drone. This system can inspect every part of a smart city from a remote location, allowing for the timely and effective management of solid waste. Thus, the proposed system can be easily integrated in the existing waste management system for smart city. The drone‐based solid waste monitoring system comprises a drone equipped with a computer vision model for resource‐constrained devices and a software application that operates the drone and analyzes the captured image or video. The system utilizes the Internet of Things (IoT) to upload the collected data to the cloud, making it easily accessible whenever necessary. The proposed drone‐based solid waste monitoring system is a promising solution for the efficient and cost‐effective management of solid waste in smart cities. The system's innovative use of drone technology and IoT provides a scalable and adaptable solution that can be customized to meet the needs of any city.

show abstract

Vision‐based garbage dumping action detection for real‐world surveillance platform

Cited by 47 publications

References 44 publications

Robust Human Pose Estimation for Rotation via Self-Supervised Learning

Robust Human Pose Estimation for Rotation via Self-Supervised Learning

Three‐stream network with context convolution module for human–object interaction detection

Efficient solid waste inspection through drone‐based aerial imagery and TinyML vision model

Contact Info

Product

Resources

About