Fruit Detection and Segmentation Using Customized Deep Learning Techniques

Tunio, Muhammad Hanif; Li, Jianping; Butt, Muhammad Hassaan Farooq; Memon, Imran; Magsi, Yumna

doi:10.1109/iccwamtip56608.2022.10016600

Cited by 2 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Advanced deep-learning techniques [20] are typically used to generate semantic information for object detection and semantic segmentation. Tunio et al [21] used the U-Net architecture based on semantic segmentation for target detection and location, achieving high accuracy. Wang et al [22] used the fully convolutional instance-aware semantic segmentation (FCIS) [23] algorithm to calculate the image boundary boxes for an input RGB image and obtained the mask information for the entire image.…”

Section: Semantic Methodsmentioning

confidence: 99%

“…When dynamic objects are present, traditional visual SLAM algorithms cannot satisfy localisation and mapping requirements. This paper categorizes dynamic visual SLAM solutions into two types: geometric [15][16][17][18][19] and semantic [20][21][22][23][24][25] methods. Geometric methods use the geometric information measured by sensors to detect and reject dynamic objects, whereas semantic methods use neural networks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SEG-SLAM: Dynamic Indoor RGB-D Visual SLAM Integrating Geometric and YOLOv5-Based Semantic Information

Cong,

Li,

Liu

et al. 2024

Sensors

View full text Add to dashboard Cite

Simultaneous localisation and mapping (SLAM) is crucial in mobile robotics. Most visual SLAM systems assume that the environment is static. However, in real life, there are many dynamic objects, which affect the accuracy and robustness of these systems. To improve the performance of visual SLAM systems, this study proposes a dynamic visual SLAM (SEG-SLAM) system based on the orientated FAST and rotated BRIEF (ORB)-SLAM3 framework and you only look once (YOLO)v5 deep-learning method. First, based on the ORB-SLAM3 framework, the YOLOv5 deep-learning method is used to construct a fusion module for target detection and semantic segmentation. This module can effectively identify and extract prior information for obviously and potentially dynamic objects. Second, differentiated dynamic feature point rejection strategies are developed for different dynamic objects using the prior information, depth information, and epipolar geometry method. Thus, the localisation and mapping accuracy of the SEG-SLAM system is improved. Finally, the rejection results are fused with the depth information, and a static dense 3D mapping without dynamic objects is constructed using the Point Cloud Library. The SEG-SLAM system is evaluated using public TUM datasets and real-world scenarios. The proposed method is more accurate and robust than current dynamic visual SLAM algorithms.

show abstract

Section: Semantic Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

SEG-SLAM: Dynamic Indoor RGB-D Visual SLAM Integrating Geometric and YOLOv5-Based Semantic Information

Cong,

Li,

Liu

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…However, in recent years, there has been a notable shift towards the application of deep learning (DL) in the analysis of SM text for disaster response [7]. DL has evinced great performance across diverse domains [10][11][12]. Different DL techniques, including CNN [13,14], LSTM [15], and Bi-LSTM [16] have been explored for disaster-related tweet classification.…”

Section: Introductionmentioning

confidence: 99%

Context-Aware Transfer Learning Approach to Detect Informative Social Media Content for Disaster Management

Saleem,

Mehrotra

2024

IJACSA

View full text Add to dashboard Cite

In the wake of disasters, timely access to accurate information about on-the-ground situation is crucial for effective disaster response. In this regard, social media (SM) like Twitter have emerged as an invaluable source of real-time user-generated data during such events. However, accurately detecting informative content from large amounts of unstructured usergenerated data under such time-sensitive circumstances remains a challenging task. Existing methods predominantly rely on noncontextual language models, which fail to accurately capture the intricate context and linguistic nuances within the disasterrelated tweets. While some recent studies have explored contextaware methods, they are based on computationally demanding transformer architectures. To strike a balance between effectiveness and computational efficiency, this study introduces a new context-aware transfer learning approach based on DistilBERT for the accurate detection of disaster related informative content on SM. Our novel approach integrates DistilBERT with a Feed Forward Neural Network (FFNN) and involves multistage finetuning of the model on balanced benchmark real-world disaster datasets. The integration of DistilBERT with an FFNN provides a simple and computationally efficient architecture, while the multistage finetuning facilitates a deeper adaptation of the model to the disaster domain, resulting in improved performance. Our proposed model delivers significant improvements compared to the state-of-the-art (SOTA) methods. This suggests that our model not only addresses the computational challenges but also enhances the contextual understanding, making it a promising advancement for accurate and efficient disaster-related informative content detection on SM platforms.

show abstract

Fruit Detection and Segmentation Using Customized Deep Learning Techniques

Cited by 2 publications

References 16 publications

SEG-SLAM: Dynamic Indoor RGB-D Visual SLAM Integrating Geometric and YOLOv5-Based Semantic Information

SEG-SLAM: Dynamic Indoor RGB-D Visual SLAM Integrating Geometric and YOLOv5-Based Semantic Information

Context-Aware Transfer Learning Approach to Detect Informative Social Media Content for Disaster Management

Contact Info

Product

Resources

About