Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63929
Volume:
10 |
5 |
May 2026
Pages:
1-3
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
MASTERS OF COMPUTER APPLICATION
BAPUJI INSTITUTE OF ENGINEERING AND TECHNOLOGY
MASTERS OF COMPUTER APPLICATION
BAPUJI INSTITUTE OF ENGINEERING AND TECHNOLOGY
The current trajectory of vehicular engineering toward SAE Level 2 and Level 3 autonomy necessitates a shift from basic assistive tools to deterministic perception frameworks. Abstract: Intelligent Lane Perception through Hybrid Neural-Geometric Architectures Unintended lane departure continues to serve as the primary catalyst for high-velocity roadway fatalities. However, legacy perception systems—constrained by Fragile Edge- Detection Heuristics—demonstrate systemic failure when confronted with Chromatic Noise, dynamic occlusion, or the degradation of retroreflective pavement markers. This project, "Intelligent Lane Detection for Next-Gen Autonomous Navigation," introduces a high-resiliency computer vision framework designed to sustain tracking fidelity across a spectrum of heterogeneous environmental variables The proposed architecture transitions away from purely linear models toward a Hybrid Neural-Geometric Synthesis. This approach integrates the high-dimensional feature extraction capabilities of Deep Convolutional Neural Networks (CNNs) with the mathematical interpretability of Higher- Order Polynomial Regression.
KEYWORDS
The "Intelligent Lane Detection for Next- Gen Vehicles" project successfully demonstrates the efficacy of combining classical computer vision techniques with advanced geometric modeling to solve a critical problem in autonomous navigation Project Synthesis and Strategic Outlook The development of the Intelligent Lane Detection system represents a transition from fragile, heuristic-based edge detection to a resilient, neural-geometric perception pipeline. by integrating HLS- domain spectral decoupling, perspective rectification (homography), and iterative polynomial regression, the framework successfully mitigates the systemic failures common in legacy ADAS architectures. · This project is 30% accuracy.
1. Bradski, G., C Kaehler, A. (2008). Learning OpenCV: Computer Vision with the OpenCV Library. O'Reilly Media. 2. Szeliski, R. (2010). Computer Vision: Algorithms and Applications. Springer-Verlag London. 3. Goodfellow, I., Bengio, Y., C Courville, A. (2016). Deep Learning. MIT Press. 4. NVIDIA Corporation. (2016). End- to-End Deep Learning for Self- Driving Cars. NVIDIA Developer Blog. 5. Gonzalez, R. C., C Woods, R. E. (2018). Digital Image Processing (4th Edition). Pearson.
Publication Date
5/25/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...