Deeply scale aggregation network for object counting

Li, He; Kong, Weihang; Zhang, Shihui

doi:10.1016/j.knosys.2020.106485

Cited by 10 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous studies have investigated object detection and counting using CNN, yielding promising results [22], [23], [24], [25], [26], [27], [28], [29]. Detection and recognition of particular objects in the room using CNN is implemented in a support system for blind people.…”

Section: Methodsmentioning

confidence: 99%

An Experimental Study on Deep Learning Technique Implemented on Low Specification OpenMV Cam H7 Device

Asmara,

Rosiani,

Mentari

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

This research aims to identify and recognize the OpenMV Camera H7. In this research, all tests were carried out using Deep Machine Learning and applied to several functions, including Face Recognition, Facial Expression Recognition, Detection and Calculation of the Number of Objects, and Object Depth Estimation. Face Expression Recognition was used in the Convolutional Neural Network to recognize five facial expressions: angry, happy, neutral, sad, and surprised. This allowed the use of a primary dataset with a 48MP resolution camera. Some scenarios are prepared to meet environment variability in the implementation, such as indoor and outdoor environments, with different lighting and distance. Most pre-trained models in each identification or recognition used mobileNetV2 since this model allows low computation cost and matches with low hardware specifications. The object detection and counting module compared two methods: the conventional Haar Cascade and the Deep Learning MobileNetV2 model. The training and validation process is not recommended to be carried out on OpenMV devices but on computers with high specifications. This research was trained and validated using selected primary and secondary data, with 1500 image data. The computing time required is around 5 minutes for ten epochs. On average, recognition results on OpenMV devices take around 0.3 - 2 seconds for each frame. The accuracy of the recognition results varies depending on the pre-trained model and the dataset used, but overall, the accuracy levels achieved tend to be very high, exceeding 96.6%.

show abstract

Section: Methodsmentioning

confidence: 99%

An Experimental Study on Deep Learning Technique Implemented on Low Specification OpenMV Cam H7 Device

Asmara,

Rosiani,

Mentari

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…The results showed that the position of the detected object could be mapped well to support the object calculation process. Li He at al [22] designed a deep-scale aggregation network dedicated to object counting, yielding commendable performance for the automatic calculation system they developed. Lastly, Zhang Yanchao, et al [23] performed fruit fruit counting using panorama and deep learning object detection methods.…”

Section: Object Countingmentioning

confidence: 99%

Detecting Objects Using Haar Cascade for Human Counting Implemented in OpenMV

Mentari,

Andrie Asmara,

Arai

et al. 2023

regist. j. ilm. teknol. sist. inf.

View full text Add to dashboard Cite

Sight is a fundamental sense for humans, and individuals with visual impairments often rely on assistance from others or tools that promote independence in performing various tasks. One crucial aspect of aiding visually impaired individuals involves the detection and counting of objects. This paper aims to develop a simulation tool designed to assist visually impaired individuals in detecting and counting human objects. The tool's implementation necessitates a synergy of both hardware and software components, with OpenMV serving as a central hardware device in this study. The research software was developed using the Haar Cascade Classifier algorithm. The research process commences with the acquisition of image data through the OpenMV camera. Subsequently, the image data undergoes several stages of processing, including the utilization of the Haar Cascade classifier method within the OpenMV framework. The resulting output consists of bounding boxes delineating the detection areas and the tally of identified human objects. The results of human object detection and counting using OpenMV exhibit an accuracy rate of 71%. Moreover, when applied to video footage, the OpenMV system yields a correct detection rate of 73% for counting human objects. In summary, this study presents a valuable tool that aids visually impaired individuals in the detection and counting of human objects, achieving commendable accuracy rates through the implementation of OpenMV and the Haar Cascade Classifier algorithm.

show abstract

Lightweight multi-scale network with attention for accurate and efficient crowd counting

Xi,

Yan

2023

Vis Comput

View full text Add to dashboard Cite

Deeply scale aggregation network for object counting

Cited by 10 publications

References 17 publications

An Experimental Study on Deep Learning Technique Implemented on Low Specification OpenMV Cam H7 Device

An Experimental Study on Deep Learning Technique Implemented on Low Specification OpenMV Cam H7 Device

Detecting Objects Using Haar Cascade for Human Counting Implemented in OpenMV

Lightweight multi-scale network with attention for accurate and efficient crowd counting

Contact Info

Product

Resources

About