Locally adaptive discounting in multi sensor occupancy grid fusion

Seeger, Christoph; Manz, Markus G.; Matters, Patrick; Hornegger, Joachim

doi:10.1109/ivs.2016.7535396

Cited by 5 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our findings serve as a remainder of the importance of fine-tuning hyperparameters and incorporating model modifications to attain high levels of accuracy in machine learning. The evaluation report generated for our research in table [6] is a crucial aspect of study as it provides a comprehensive assessment of classification model's performance metrics such as accuracy, precision, recall, and F1-score for each class. This analysis will help us to identify the areas of strength and weaknesses of our model and make improvements accordingly.…”

Section: Fig 6: Confusion Matrix For Road Surface Classificationmentioning

confidence: 99%

“…Fig 1: Types of Assistive Device for VIPIn t h e paper6 ) the author Suggested an automatic survey of systems for the paved and unpaved road surface classification analyzing the data which is coming from the accelerometer, gyroscope, and compass. The author used different machine learning algorithms like SVM (Support Vector Machine), HMM (Hidden Markov Model), and ResNet-based CNN for implementing the road surface classification model.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Road Surface Quality Detection Using Light Weight Neural Network for Visually Impaired Pedestrian

Chaudhary,

Dr. PrabhatVerma

2023

Evergreen

View full text Add to dashboard Cite

Visually impaired pedestrians often face challenges navigating outdoor environments due to difficulties in identifying road surface quality. To enhance safety, we propose a deep learningbased architecture that can be easily deployed on mobile devices for real-time assistance, potentially reducing road injuries. Our suggested approach builds upon the pre-trained CNN, MobileNetV2, by adding supplementary layers without increasing computational complexity. The model is evaluated on unseen images, with results indicating improved classification performance in terms of F1-score, recall, accuracy, and precision compared to alternative models, including Random Forest, ResNet, EfficientNet, and InceptionNet. Our proposed model achieves 93.20% accuracy relative to MobileNetV2. However, the architecture does not account for obstacles on road surfaces, which could also cause injuries. The modified MobileNetV2 architecture effectively classifies road surfaces to assist visually impaired pedestrians and can be seamlessly integrated into mobile devices. Our work presents a novel, efficient, and low-power system with enhanced accuracy for road quality classification, suitable for deployment on diverse devices such as smartphones.

show abstract

Section: Fig 6: Confusion Matrix For Road Surface Classificationmentioning

confidence: 99%

mentioning

confidence: 99%

Road Surface Quality Detection Using Light Weight Neural Network for Visually Impaired Pedestrian

Chaudhary,

Dr. PrabhatVerma

2023

Evergreen

View full text Add to dashboard Cite

show abstract

“…neighboring cells is considered to improve the obstacle detection for narrow vertical field of view sensors. The same authors extend the fusion strategy in [110] using an obstacle association concept between different sensor grid maps by evaluating their individual covariance with a discounting strategy of imprecise sensor grids. However, the obstacle association is primarily intended for highway scenarios, whereas more cluttered urban scenarios might result in wrong associations.…”

Section: Known Robot Posementioning

confidence: 99%

Grid-Based Object Tracking

Steyer¹

2021

View full text Add to dashboard Cite

Mobile robots require an accurate environment perception to plan intelligent maneuvers and avoid collisions. This thesis presents a novel multi sensor environment estimation strategy that fully combines tracking moving objects and mapping the static environment. The basic idea is to fuse and accumulate measurement data by a dynamic occupancy grid model, whereas moving objects are extracted subsequently based on that generic low-level grid representation. Overall, this work results in a robust and consistent estimation of arbitrary objects and obstacles, which is demonstrated in the context of autonomous driving in complex unstructured environments. Contents Notations VIII Abstract XI 1 Introduction 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Challenges of Multi-Sensor Environment Perception . . . . . . . . . . . . . 2 1.3 Main Contribution and Outline of This Work . . . . . . . . . . . . . . . . 8 2 Measurement Grid Representation and Fusion 13 2.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.1.1 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.1.2...

show abstract

“…In the paper [9], the authors also mention the importance of knowing the surface type for interpreting the environment while driving. However, the paper provides a different approach to road classification as it uses occupancy grids as data for the classification.…”

Section: Introductionmentioning

confidence: 99%

Application of Convolutional Neural Networks for Road Type Classification

et al. 2023

View full text Add to dashboard Cite

This paper presents an application of convolutional neural networks (CNN) in autonomous driving system, which represents the capacity of a vehicle to operate mostly or entirely autonomously, with or without human assistance. After basic introduction of CNN, we design and apply CNN-based algorithm in road type classification problem. The performed simulations show that satisfactory results can be achieved even with little data available.

show abstract

Locally adaptive discounting in multi sensor occupancy grid fusion

Cited by 5 publications

References 22 publications

Road Surface Quality Detection Using Light Weight Neural Network for Visually Impaired Pedestrian

Road Surface Quality Detection Using Light Weight Neural Network for Visually Impaired Pedestrian

Grid-Based Object Tracking

Application of Convolutional Neural Networks for Road Type Classification

Contact Info

Product

Resources

About