التفاصيل البيبلوغرافية
العنوان: |
Enhancing Deep Learning-Based Segmentation Accuracy through Intensity Rendering and 3D Point Interpolation Techniques to Mitigate Sensor Variability. |
المؤلفون: |
Kim MJ; Graduate School of Automotive Engineering, Kookmin University, Seoul 02707, Republic of Korea., Kim S; Moovita Pte Ltd., Block 44, 535 Clementi Rd., Singapore 599489, Singapore., Lee B; Moovita Pte Ltd., Block 44, 535 Clementi Rd., Singapore 599489, Singapore., Kim J; Department of Automotive and IT Convergence, Kookmin University, Seoul 02707, Republic of Korea. |
المصدر: |
Sensors (Basel, Switzerland) [Sensors (Basel)] 2024 Jul 11; Vol. 24 (14). Date of Electronic Publication: 2024 Jul 11. |
نوع المنشور: |
Journal Article |
اللغة: |
English |
بيانات الدورية: |
Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: PubMed not MEDLINE; MEDLINE |
أسماء مطبوعة: |
Original Publication: Basel, Switzerland : MDPI, c2000- |
مستخلص: |
In the context of LiDAR sensor-based autonomous vehicles, segmentation networks play a crucial role in accurately identifying and classifying objects. However, discrepancies between the types of LiDAR sensors used for training the network and those deployed in real-world driving environments can lead to performance degradation due to differences in the input tensor attributes, such as x, y, and z coordinates, and intensity. To address this issue, we propose novel intensity rendering and data interpolation techniques. Our study evaluates the effectiveness of these methods by applying them to object tracking in real-world scenarios. The proposed solutions aim to harmonize the differences between sensor data, thereby enhancing the performance and reliability of deep learning networks for autonomous vehicle perception systems. Additionally, our algorithms prevent performance degradation, even when different types of sensors are used for the training data and real-world applications. This approach allows for the use of publicly available open datasets without the need to spend extensive time on dataset construction and annotation using the actual sensors deployed, thus significantly saving time and resources. When applying the proposed methods, we observed an approximate 20% improvement in mIoU performance compared to scenarios without these enhancements. |
References: |
Sensors (Basel). 2019 Mar 26;19(6):. (PMID: 30917566) |
معلومات مُعتمدة: |
P0008751 Ministry of Trade, Industry and Energy |
فهرسة مساهمة: |
Keywords: 3D segmentation; LiDAR sensor; data annotation; deep learning; intensity rendering; object detection |
تواريخ الأحداث: |
Date Created: 20240727 Latest Revision: 20240729 |
رمز التحديث: |
20240729 |
مُعرف محوري في PubMed: |
PMC11280802 |
DOI: |
10.3390/s24144475 |
PMID: |
39065873 |
قاعدة البيانات: |
MEDLINE |