Daanish Case Studies

See how we helped businesses across the globe to change and transform the world by bringing the new to life with the latest technologies.

Greenzie

Greenzie specializes in autonomous lawn mowing technology tailored for expansive applications. Their core challenge revolves around leveraging AI cameras to ensure precision and safety in mowing.

Greenzie places a paramount focus on machine learning algorithms to achieve essential discerning cues for blade activation (“blades on”) in grassy scenarios and deactivation (“blades off”) in the presence of obstacles or objects.

This intricate process heavily relies on amassing vast datasets and integrating object detection, recognition, and semantic segmentation technologies. Moreover, Greenzie incorporates Luxonis Cameras with sophisticated features like depth analysis, 9-axis IMU (Inertial Measurement Unit), and feature tracking systems.

These elements synergize to empower their AI-driven cameras with comprehensive awareness, allowing the mowers to navigate diverse terrains autonomously while safeguarding both the equipment and surrounding properties from potential damage.

Greenzie used a multidimensional approach that combines innovative AI vision with advanced sensors to redefine the effectiveness and safety standards in large-scale lawn maintenance.

Lantern

Lantern, an innovative technology, addresses the growing challenges faced by road maintenance crews and lane painters. With the surge in electric vehicle usage, the demand for clear and distinct lane markings has amplified, necessitating frequent lane painting. However, this task often occurs amidst traffic, posing safety risks due to slow-moving painter vehicles. Lantern’s solution involves AI-powered cameras that measure approaching vehicle speed, distance, and position. This data triggers a sequence of warnings to alert distracted drivers, mitigating collision risks. Crucially, these variables are measured from a significant distance, allowing adequate time for vehicles to slow down and emphasizing the importance of superior depth perception performance.

Accurate segmentation of road lanes and precise vehicle differentiation are critical challenges. Lantern’s technology addresses these challenges by employing AI algorithms capable of properly segmenting lanes and accurately distinguishing between various vehicles.

By implementing Lantern’s AI-driven system, road maintenance crews and lane painters experience increased safety during painting tasks, while road users benefit from improved awareness and reduced collision risks, fostering more efficient road maintenance processes in alignment with the evolving demands of electric vehicle navigation.

Cobra Vision

Cobra Vision, a construction company specializing in power substations, has embraced AI technology, specifically AI cameras, to revolutionize road maintenance and enhance the efficiency of painters on-site. Their primary focus lies in minimizing collisions through the implementation of various AI techniques such as semantic segmentation. By employing this technology, Cobra Vision can accurately identify and differentiate people, vehicles, and structures in real-time, ensuring enhanced safety measures.

Moreover, their AI-based approach extends to improving worker safety by actively monitoring whether individuals on the job site are wearing appropriate safety equipment. This proactive measure significantly reduces the risk of accidents and ensures compliance with safety protocols.

The incorporation of corner detection, pose estimation, spatial depth/location, and object tracking further amplifies the capabilities of Cobra Vision’s AI system. This comprehensive utilization of AI cameras optimizes road maintenance tasks and facilitates painters’ work by providing a safer environment and efficient monitoring, ultimately leading to heightened productivity and reduced risks on construction sites.

NUST 

The Safe Rail project, sponsored by NUST (National University of Science and Technology) targets increased rail track safety that aims to prevent tragic accidents. DAANISH Technologies, partnering with Luxonis, uses AI-powered imaging and algorithms to enhance track inspection for various failures including rail gauge, fish plate, and sleeper defects critical for railway safety. Luxonis contributes advanced imaging and supports algorithm development. NUST’s Robotics Research Center collaborates on this, addressing challenges of railway inspection and defects identification. They employed Luxonis OAK-D-POE Cameras integrated into inspection vehicles, the team designed specialized equipment for real-time defect analysis. Challenges included customizing mounts and algorithm accuracy. Milestones encompass camera integration, algorithm optimization, and real-world testing, expected by 2025. Mr. Ahmed Said of DAANISH Technologies leads this initiative, ensuring comprehensive rail safety measures for seamless transportation and preventing further tragedies.

 

Ready to find out more?

Ask us about our free trial of our solutions and audit services.  Our team of professional are waiting anxiously to build the relationship with you.