Computer Vision based Animal Collision Avoidance Framework for Autonomous Vehicles

Gupta, Savyasachi; Chand, Dhananjai; Kavati, Ilaiah

doi:10.1007/978-981-16-1103-2_21

Cited by 7 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They achieved accuracy of 94%. Gupta et al [42] used the Mask R-CNN model with a pre-trained network ResNet-101 to detect two animal species (cows and dogs). They achieved an average precision of 79.47% in detecting cows and 81.09% in detecting dogs.…”

Section: Animal Species Detectionmentioning

confidence: 99%

“…an activation function Softmax, which converts the output values to conditional probabilities (normalized classification scores) for prediction, where each value ranges between 0 and 1 and all values sum to one [3,42]. The architecture of CNN has the capability to learn and extract object features, and to merge several tasks together, for example, object detection and segmentation.…”

Section: Regular Cnnmentioning

confidence: 99%

See 1 more Smart Citation

A Performance Comparison and Enhancement of Animal Species Detection in Images with Various R-CNN Models

Ibraheam

Gebali

et al. 2021

View full text Add to dashboard Cite

Object detection is one of the vital and challenging tasks of computer vision. It supports a wide range of applications in real life, such as surveillance, shipping, and medical diagnostics. Object detection techniques aim to detect objects of certain target classes in a given image and assign each object to a corresponding class label. These techniques proceed differently in network architecture, training strategy and optimization function. In this paper, we focus on animal species detection as an initial step to mitigate the negative impacts of wildlife–human and wildlife–vehicle encounters in remote wilderness regions and on highways. Our goal is to provide a summary of object detection techniques based on R-CNN models, and to enhance the performance of detecting animal species in accuracy and speed, by using four different R-CNN models and a deformable convolutional neural network. Each model is applied on three wildlife datasets, results are compared and analyzed by using four evaluation metrics. Based on the evaluation, an animal species detection system is proposed.

show abstract

Section: Animal Species Detectionmentioning

confidence: 99%

Section: Regular Cnnmentioning

confidence: 99%

A Performance Comparison and Enhancement of Animal Species Detection in Images with Various R-CNN Models

Ibraheam

Gebali

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Object detection algorithms for AVs focus primarily on road signs, pedestrians, cyclists, or other vehicles [e.g., 52-58], with comparatively fewer methods designed for animal detection [59][60][61][62].…”

Section: Obstacle Detection and Motion Trackingmentioning

confidence: 99%

“…Saxena et al [60], based on a Single Shot Detector and Faster Region-based CNN (Faster R-CNN) algorithm, improve object detection speed but do not incorporate motion tracking. Gupta et al [61] incorporate motion tracking and prediction, leveraging the Mask R-CNN model for multiple species and using lane detection to develop a predictive feedback mechanism, but require clear lane demarcation and only achieved an accuracy of 81%. All of these methods require either visible-light or thermal cameras, and the majority are trained on a single species [62][63][64][65].…”

Section: Obstacle Detection and Motion Trackingmentioning

confidence: 99%

“…The development of more appropriate animal detection methods is also necessary. Relying only on algorithms tailored for human detection may lead to inaccurate interpretations of animal behavior or their impending motion, and current animal-specific methods still face many obstacles: relatively high response times only applicable at low vehicle speeds [59,62], the need for clear lane demarcation [61], no motion tracking [60], or limited training datasets [62,65].…”

Section: Infrastructure and Technical Limitationsmentioning

confidence: 99%

See 1 more Smart Citation

Emerging opportunities for wildlife with sustainable autonomous transportation

Silva¹,

Calabrese²

2021

Preprint

View full text Add to dashboard Cite

Autonomous vehicles (AV) are expected to play a key role in the future of transportation, introducing a disruptive yet potentially beneficial change for vehicle-wildlife interactions. However, this assumption has not been critically examined. Here, we introduce a new conceptual framework covering the intersection between AV technological innovation and wildlife conservation to reduce wildlife-vehicle collisions. We suggest future research within this framework to focus on developing robust warning systems and animal detection methods for AV systems, and to incorporate wildlife-vehicle interactions into decision-making algorithms. With large-scale deployment a looming reality, it is vital to incorporate conservation and sustainability into the societal, ethical, and legal implications of AV technology. We appeal for further debate and interdisciplinary collaborations between scientists, developers, and policymakers.

show abstract

Emerging opportunities for wildlife conservation with sustainable autonomous transportation

Silva,

Calabrese

2023

Frontiers in Ecol & Environ

View full text Add to dashboard Cite

Autonomous vehicles (AVs) are expected to play a key role in the future of transportation, and to introduce a disruptive yet potentially beneficial change for wildlife–vehicle interactions. However, this assumption has not been critically examined, and reducing the number of wildlife–vehicle collisions (WVCs) may be beyond current technological capabilities. Here, we introduce a conceptual framework encompassing the intersection between AV technology and wildlife conservation to reduce WVCs. Our proposed framework integrates the development of robust warning systems and animal detection methods for AV systems, and the incorporation of wildlife–vehicle interactions into decision‐making algorithms. With large‐scale AV deployment a looming reality, it is vital to incorporate conservation and sustainability into the societal, ethical, and legal implications of AV technology. We intend our framework to help ecologists and conservationists foster the necessary interdisciplinary collaborations with AV developers and policy makers to reduce WVCs and concomitant biodiversity loss.

show abstract

Computer Vision based Animal Collision Avoidance Framework for Autonomous Vehicles

Cited by 7 publications

References 9 publications

A Performance Comparison and Enhancement of Animal Species Detection in Images with Various R-CNN Models

A Performance Comparison and Enhancement of Animal Species Detection in Images with Various R-CNN Models

Emerging opportunities for wildlife with sustainable autonomous transportation

Emerging opportunities for wildlife conservation with sustainable autonomous transportation

Contact Info

Product

Resources

About