Performance of MobileNetV3 Transfer Learning on Handheld Device-based Real-Time Tree Species Identification

Hussain, Ambreen; Barua, Bidushi; Osman, Ahmed; Abozariba, Raouf; Asyhari, A. Taufiq

doi:10.23919/icac50006.2021.9594222

Cited by 14 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Influenced by factors, such as network independence, computing load and time requirements, this paper selects MobileNetV3 to extract deep image features. The MobileNetV3 network can run independently on handheld devices without Internet access, 30 which is very suitable for mobile and embedded devices.…”

Section: Our Approachmentioning

confidence: 99%

Research on objective assessment of dual-band color night vision fusion image quality based on scene understanding

Gao,

Yi,

Tian

et al. 2023

Opt. Eng.

View full text Add to dashboard Cite

The color quality and sharpness of the dual-band color fusion images have the greatest impact on the audience's understanding of the scene content. Traditional image quality assessment (IQA) methods focus on the luminance contrast of image and attach limited attention to pixel-wise relationship. As a result, these methods perform poorly on color-related distortions. A objective assessment model for the comprehensive quality of fusion images is proposed. According to the correlation between the gray level co-occurrence matrix (GLCM) and the image color, the model extracts the homogeneity, angular second moment, and contrast of the GLCM as the image color quality features. Gradient-weighted class activation mapping is used to calculate the heat map, reflecting the visual saliency of each region. We use the visual saliency weight of each region to weight the rotation and uniform invariant local binary pattern histograms of the corresponding regions to obtain sharpness features. The experimental results show that the performance of the proposed method is better than the existing eight no-reference IQA models.

show abstract

Section: Our Approachmentioning

confidence: 99%

Research on objective assessment of dual-band color night vision fusion image quality based on scene understanding

Gao,

Yi,

Tian

et al. 2023

Opt. Eng.

View full text Add to dashboard Cite

show abstract

“…Compared with the traditional convolutional neural network, MobileNet has the advantages of fewer parameters and lower delay. At present, MobileNet series networks include MobileNetv1, MobileNetv2 ( Huu et al., 2022 ; Młodzianowski, 2022 ) and MobileNetv3 ( Howard et al., 2019 ; Hussain et al., 2021 ; Zhao and Wang, 2022 ; Zhao et al., 2022 ). MobileNetv3 is Google’s new invention after MobileNetv2, and its main improvement is to add SE-net after the deep separable convolution in MobileNetv2, which automatically obtains the importance of each feature channel by learning, and suppresses some feature information that is not useful for the current task.…”

Section: Related Workmentioning

confidence: 99%

A lightweight method for maize seed defects identification based on Convolutional Block Attention Module

Li,

Chen,

Jing

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

Maize is widely cultivated and planted all over the world, which is one of the main food resources. Accurately identifying the defect of maize seeds is of great significance in both food safety and agricultural production. In recent years, methods based on deep learning have performed well in image processing, but their potential in the identification of maize seed defects has not been fully realized. Therefore, in this paper, a lightweight and effective network for maize seed defect identification is proposed. In the proposed network, the Convolutional Block Attention Module (CBAM) was integrated into the pretrained MobileNetv3 network for extracting important features in the channel and spatial domain. In this way, the network can be focused on useful feature information, and making it easier to converge. To verify the effectiveness of the proposed network, a total of 12784 images was collected, and 7 defect types were defined. Compared with other popular pretrained models, the proposed network converges with the least number of iterations and achieves the true positive rate is 93.14% and the false positive rate is 1.14%.

show abstract

“…However, these applications depend on the available network connection (limited in remote forests and rural areas) to evaluate the images using trained models on the servers [ 49 ]. To overcome this issue, a lightweight model of MobileNetV3 was embedded in an Android mobile application for offline tree species classification [ 50 ]. The authors of [ 51 , 52 , 53 ] focused on tree height and girth measurement using computer vision and image processing techniques.…”

Section: Literature Reviewmentioning

confidence: 99%

Evaluating the Forest Ecosystem through a Semi-Autonomous Quadruped Robot and a Hexacopter UAV

Idrissi

Hussain

Barua

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Accurate and timely monitoring is imperative to the resilience of forests for economic growth and climate regulation. In the UK, forest management depends on citizen science to perform tedious and time-consuming data collection tasks. In this study, an unmanned aerial vehicle (UAV) equipped with a light sensor and positioning capabilities is deployed to perform aerial surveying and to observe a series of forest health indicators (FHIs) which are inaccessible from the ground. However, many FHIs such as burrows and deadwood can only be observed from under the tree canopy. Hence, we take the initiative of employing a quadruped robot with an integrated camera as well as an external sensing platform (ESP) equipped with light and infrared cameras, computing, communication and power modules to observe these FHIs from the ground. The forest-monitoring time can be extended by reducing computation and conserving energy. Therefore, we analysed different versions of the YOLO object-detection algorithm in terms of accuracy, deployment and usability by the EXP to accomplish an extensive low-latency detection. In addition, we constructed a series of new datasets to train the YOLOv5x and YOLOv5s for recognising FHIs. Our results reveal that YOLOv5s is lightweight and easy to train for FHI detection while performing close to real-time, cost-effective and autonomous forest monitoring.

show abstract

Performance of MobileNetV3 Transfer Learning on Handheld Device-based Real-Time Tree Species Identification

Cited by 14 publications

References 25 publications

Research on objective assessment of dual-band color night vision fusion image quality based on scene understanding

Research on objective assessment of dual-band color night vision fusion image quality based on scene understanding

A lightweight method for maize seed defects identification based on Convolutional Block Attention Module

Evaluating the Forest Ecosystem through a Semi-Autonomous Quadruped Robot and a Hexacopter UAV

Contact Info

Product

Resources

About