Autonomous Car Driving Using Deep Learning

Darapaneni, Narayana; R, Pratosh Raj; Paduri, Anwesh Reddy; Anand, Emmanuel; Rajarathinam, Kumar; Eapen, Prem Thomas; K, Sethuraman.; Krishnamurthy, Sharath

doi:10.1109/icsccc51823.2021.9478090

Cited by 14 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the implementation perspective, for the NUMSnet model, we applied batch normalization to encoder layers only and dropout at layers X(4,1) and X(5,1) only (GitHub code available at https://github.com/sohiniroych/NUMSnet, accessed on 12 June 2023). In addition, the widths of kernels per depth layer for the NUMSnet model are [5,70,140,280,560], similar to those of the wUnet model. This process of transmitting and concatenating layer-specific features with those of the subsequent ordered images generates finer boundaries for ROIs.…”

Section: The Numsnet Modelmentioning

confidence: 82%

“…For semantic segmentation tasks, where objects or regions of interest (ROIs) are enclosed within a closed polygon, the Unet model [3] and its variants have been a widely preferred method owing to the relatively low computational complexity and high adaptability across use cases due to short-and long-range skip connections. This allows the Unet and variant models to be well trained from only a few hundred images, as opposed to requiring thousands of annotated images for deep learning models with dense connections, which are preferred in the realtime use cases of autonomous driving and augmented reality [4,5]. However, segmenting multiple ROIs with varying sizes and shapes in continuous image stacks or videos can be challenging due to the biases introduced by foreground regions with varying sizes and can result in jittery detection across subsequent frames.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

NUMSnet: Nested-U Multi-Class Segmentation Network for 3D Medical Image Stacks

Roychowdhury

2023

Information

View full text Add to dashboard Cite

The semantic segmentation of 3D medical image stacks enables accurate volumetric reconstructions, computer-aided diagnostics and follow-up treatment planning. In this work, we present a novel variant of the Unet model, called the NUMSnet, that transmits pixel neighborhood features across scans through nested layers to achieve accurate multi-class semantic segmentation with minimal training data. We analyzed the semantic segmentation performance of the NUMSnet model in comparison with several Unet model variants in the segmentation of 3–7 regions of interest using only 5–10% of images for training per Lung-CT and Heart-CT volumetric image stack. The proposed NUMSnet model achieves up to 20% improvement in segmentation recall, with 2–9% improvement in Dice scores for Lung-CT stacks and 2.5–16% improvement in Dice scores for Heart-CT stacks when compared to the Unet++ model. The NUMSnet model needs to be trained with ordered images around the central scan of each volumetric stack. The propagation of image feature information from the six nested layers of the Unet++ model are found to have better computation and segmentation performance than the propagation of fewer hidden layers or all ten up-sampling layers in a Unet++ model. The NUMSnet model achieves comparable segmentation performance to previous works while being trained on as few as 5–10% of the images from 3D stacks. In addition, transfer learning allows faster convergence of the NUMSnet model for multi-class semantic segmentation from pathology in Lung-CT images to cardiac segmentation in Heart-CT stacks. Thus, the proposed model can standardize multi-class semantic segmentation for a variety of volumetric image stacks with a minimal training dataset. This can significantly reduce the cost, time and inter-observer variability associated with computer-aided detection and treatment.

show abstract

Section: The Numsnet Modelmentioning

confidence: 82%

Section: Introductionmentioning

confidence: 99%

NUMSnet: Nested-U Multi-Class Segmentation Network for 3D Medical Image Stacks

Roychowdhury

2023

Information

View full text Add to dashboard Cite

show abstract

“…These include navigating cluttered or dynamically evolving environments and applications demanding a semantic understanding of the environment (Guebli & Belkhir, 2021). Its utility is notably prominent in applications like autonomous vehicles, where the system must adapt to a wide variety of conditions on the fly (Darapaneni, N. et al, 2021).…”

Section: Deep Learning-based Fusionmentioning

confidence: 99%

Intelligent Systems in Motion

Cai,

Qin,

et al. 2023

International Journal on Semantic Web and Information Systems

View full text Add to dashboard Cite

Simultaneous localization and mapping (SLAM) serves as a cornerstone in autonomous systems and has seen exponential growth in its roles, particularly in facilitating advanced path planning solutions. One emerging avenue of research that is rapidly evolving is the incorporation of multi-sensor fusion techniques to enhance SLAM-based path planning. The paper initiates with a thorough review of various sensor types and their attributes before covering a broad spectrum of both traditional and contemporary algorithms for multi-sensor fusion within SLAM. Performance evaluation metrics pertinent to SLAM and sensor fusion are explored. A special focus is laid on the interconnected roles and applications of multi-sensor fusion in SLAM-based path planning, discussing its significance in navigation scenarios as well as addressing challenges such as computational burden and real-time implementation. This paper sets the stage for future developments in creating more robust, resilient, and efficient SLAM-based path planning systems enabled by multi-sensor fusion.

show abstract

Adaptive Image Adversarial Example Detection Based on Class Activation Mapping

Wang,

Li,

2024

Data and Applications Security and Privacy XXXVIII

View full text Add to dashboard Cite

Autonomous Car Driving Using Deep Learning

Cited by 14 publications

References 5 publications

NUMSnet: Nested-U Multi-Class Segmentation Network for 3D Medical Image Stacks

NUMSnet: Nested-U Multi-Class Segmentation Network for 3D Medical Image Stacks

Intelligent Systems in Motion

Adaptive Image Adversarial Example Detection Based on Class Activation Mapping

Contact Info

Product

Resources

About