Intelligent Systems Using Sensors and/or Machine Learning to Mitigate Wildlife–Vehicle Collisions: A Review, Challenges, and New Perspectives

Abstract

Worldwide, the persistent trend of human and animal life losses, as well as damage to properties due to wildlife–vehicle collisions (WVCs) remains a significant source of concerns for a broad range of stakeholders. To mitigate their occurrences and impact, many approaches are being adopted, with varying successes. Because of their increased versatility and increasing efficiency, Artificial Intelligence-based methods have been experiencing a significant level of adoption. The present work extensively reviews the literature on intelligent systems incorporating sensor technologies and/or machine learning methods to mitigate WVCs. Included in our review is an investigation of key factors contributing to human–wildlife conflicts, as well as a discussion of dominant state-of-the-art datasets used in the mitigation of WVCs. Our study combines a systematic review with bibliometric analysis. We find that most animal detection systems (excluding autonomous vehicles) are relying neither on state-of-the-art datasets nor on recent breakthrough machine learning approaches. We, therefore, argue that the use of the latest datasets and machine learning techniques will minimize false detection and improve model performance. In addition, the present work covers a comprehensive list of associated challenges ranging from failure to detect hotspot areas to limitations in training datasets. Future research directions identified include the design and development of algorithms for real-time animal detection systems. The latter provides a rationale for the applicability of our proposed solutions, for which we designed a continuous product development lifecycle to determine their feasibility.

Emerging opportunities for wildlife conservation with sustainable autonomous transportation

“…The reduction of WVC events requires modifications at three levels: infrastructure, society, and transport systems (Figure 3). First, crucial upgrades to existing infrastructure will extend to the implementation of specific mitigation measures, and can likewise facilitate AV deployment (eg clear lane markings; Liu et al 2019;Nandutu et al 2022). Although some measures require a large initial investment, WVC prevention offsets their cost within 16-40 years, or earlier for animal mortality hotspots (Ascensão et al 2021).…”

Ultrasonic Sensor-Based Embedded System for Vehicular Collusion Detection and Alert

“…Using machine learning techniques, the approach detects potential collisions and uses a combination of sensors, such as radar and lidar, to collect data about the vehicle's surroundings. This data is then processed using machine learning algorithms to detect potential hazards, such as other vehicles or obstacles on the road [5]. The machine learning algorithms used in these systems are typically trained on large datasets of sensor data, allowing them to recognize patterns and identify potential hazards with a high degree of accuracy.…”

“…For instance, the approach can adapt to changing road conditions and can detect potential hazards that may not be immediately visible to the driver. It can also learn from real-world driving data, allowing the system to continually improve its accuracy and effectiveness [5]. Intelligent collision detection systems using machine learning algorithms are an important development in collision avoidance technology, and have the potential to significantly improve road safety and reduce the risk of accidents.…”

“…The system detects impediments present on the roadway and responds by engaging the vehicle's braking mechanism. The advancement in this approach is that it can facilitate the circumvention of impediments on the roadway [5] [6]. The integration of a sensor, microcontroller, and alert system has demonstrated significant efficacy in mitigating collision-related concerns.…”

Optimization of Wildfire Localization Using a Trilateration-Based Nelder-Mead Algorithm in a Wireless Sensor Network

“…In other words, some harsh environments may prevent the use of GPS [31]. The reader is referred to some researchers [32][33][34] for more details regarding GPS challenges. Hence, in special circumstances, the application of the anchor node technique outweighs the corresponding fully GPS-based localization system.…”