A robust lane detection and departure warning system

Haloi, Mrinal; Kumar, Shubham

doi:10.1109/ivs.2015.7225674

Cited by 37 publications

(22 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Figure 1, a conventional residual block [23] has 2 pre-activation convolutions in it's residual branch, the accumulation of which we denote by F R (X l ) and identity mapping, H(X l ) = X l . The conventional Residual operations are demonstrated in Equation (1). In stead of using a bunch of these residual blocks we tried using a fewer with newly designed skip connections that are capable of learning more interesting features.…”

Section: A Skip Connections In Convolutional Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Total Recall: Understanding Traffic Signs Using Deep Convolutional Neural Network

Saha

Kamran

Sabbir

2018

2018 21st International Conference of Computer and Information Technology (ICCIT)

View full text Add to dashboard Cite

Recognizing Traffic Signs using intelligent systems can drastically reduce the number of accidents happening worldwide. With the arrival of Self-driving cars it has become a staple challenge to solve the automatic recognition of Traffic and Hand-held signs in the major streets. Various machine learning techniques like Random Forest, SVM as well as deep learning models has been proposed for classifying traffic signs. Though they reach state-of-the-art performance on a particular dataset, but fall short of tackling multiple Traffic Sign Recognition benchmarks. In this paper, we propose a novel and one-for-all architecture that aces multiple benchmarks with better overall score than the state-of-the-art architectures. Our model is made of residual convolutional blocks with hierarchical dilated skip connections joined in steps. With this we score 99.33% Accuracy in German sign recognition benchmark and 99.17% Accuracy in Belgian traffic sign classification benchmark. Moreover, we propose a newly devised dilated residual learning representation technique which is very low in both memory and computational complexity.

show abstract

Section: A Skip Connections In Convolutional Neural Networkmentioning

confidence: 99%

“…As Self-driving cars are being introduced in major cities, intelligent traffic signs recognition has become an essential part of any autonomous driver-less vehicles [1]- [4]. Transitioning from a vehicle with driver to a driver-less vehicle should come in steps.…”

Section: Introductionmentioning

confidence: 99%

Total Recall: Understanding Traffic Signs Using Deep Convolutional Neural Network

Saha

Kamran

Sabbir

2018

2018 21st International Conference of Computer and Information Technology (ICCIT)

View full text Add to dashboard Cite

show abstract

“…Canny edges [ 15 ] are composed of pixels with strong gradient magnitudes. The steerable Gaussian filter [ 5 , 16 , 17 , 18 , 19 , 20 , 21 ] extracts edge features by utilizing the gradient orientation information. However, the thresholds to determine edges in these methods are manually set to be constant, which causes the method to be inapplicable to dynamically-changing traffic scenes.…”

Section: Related Workmentioning

confidence: 99%

“…Filtering methods based on geometry constraints are also explored to refine line features [ 5 , 9 , 10 , 23 , 36 , 37 ]. For example, the IPM-based methods [ 3 , 9 , 18 , 20 , 25 , 27 , 30 , 31 , 32 , 33 , 35 , 36 , 38 , 39 , 40 , 41 , 42 ] eliminate noise by searching for horizontal intensity bumps in bird’s eye-view images based on the assumptions of parallel lane boundaries and flat roads. However, if roads are not flat, with those methods, lane boundaries will be mapped as nonparallel lines on the bird’s eye-view images, thereby leading to false detection.…”

Section: Related Workmentioning

confidence: 99%

Efficient Lane Boundary Detection with Spatial-Temporal Knowledge Filtering

Nan

Wei

et al. 2016

Sensors

View full text Add to dashboard Cite

Lane boundary detection technology has progressed rapidly over the past few decades. However, many challenges that often lead to lane detection unavailability remain to be solved. In this paper, we propose a spatial-temporal knowledge filtering model to detect lane boundaries in videos. To address the challenges of structure variation, large noise and complex illumination, this model incorporates prior spatial-temporal knowledge with lane appearance features to jointly identify lane boundaries. The model first extracts line segments in video frames. Two novel filters—the Crossing Point Filter (CPF) and the Structure Triangle Filter (STF)—are proposed to filter out the noisy line segments. The two filters introduce spatial structure constraints and temporal location constraints into lane detection, which represent the spatial-temporal knowledge about lanes. A straight line or curve model determined by a state machine is used to fit the line segments to finally output the lane boundaries. We collected a challenging realistic traffic scene dataset. The experimental results on this dataset and other standard dataset demonstrate the strength of our method. The proposed method has been successfully applied to our autonomous experimental vehicle.

show abstract

“…In response to such stern problems, Lane Keeping Assistance (LKA) [14]; Lane Departure Warning (LDW) [15]- [17]; Lane Following (LF) [18], [19]; Lateral Control (LC); Intelligent Cruise Control (ICC); Collision Warning (CW) [20]; and Autonomous Vehicle Guidance [21] are called for by vehicle manufacturer industries to enhance the vehicle safety.…”

Section: Introductionmentioning

confidence: 99%

Experimental of Vision-based Lane Markings Segmentation Methods in Lane Detection Application

Ping¹,

Hossen²,

Imaduddin³

et al. 2019

JESTR

View full text Add to dashboard Cite

Lane departure collisions have contributed into the traffic accidents that cause millions of injuries and tens of thousands of casualties per year worldwide. Hence, a vision-based lane detection framework (VBLD) is proposed to detect lane markings on the road for unindented lane departure. The proposed VBLD framework is composed of colour space conversion, region of interest, lane marking segmentation, Hough transformation and peak detection, reverse Hough transformation, and draw detected lines on original image. Besides, finite impulse response saturation autothreshold (FIRSA) lane marking segmentation method is also proposed for lane edges extraction. For performance evaluation on the proposed VBLD framework and proposed FIRSA lane markings segmentation method, real-life datasets of road footages are collected using an instrumented vehicle. The outputs of lane detection frames from Clip #1, #2, #3, and #4 involving variety of road conditions are evaluated using detection rate, false positive rate, and false negative rate assessment metrics where the number of frames are manually counted using visual inspection. Experimental results have shown the evidences of the proposed VBLD framework using proposed FIRSA lane markings segmentation method obtained satisfactory lane detection results compared to benchmark lane marking segmentation methods.

show abstract

A robust lane detection and departure warning system

Cited by 37 publications

References 20 publications

Total Recall: Understanding Traffic Signs Using Deep Convolutional Neural Network

Total Recall: Understanding Traffic Signs Using Deep Convolutional Neural Network

Efficient Lane Boundary Detection with Spatial-Temporal Knowledge Filtering

Experimental of Vision-based Lane Markings Segmentation Methods in Lane Detection Application

Contact Info

Product

Resources

About