KOCA VENTURES LTD
71-75, Shelton Street, Covent Garden
London, WC2H 9JQ, UNITED KINGDOM
Registered in UNITED KINGDOM, Number 16231043
Portfolio
Discover how we transform businesses with cutting-edge AI, computer vision, and enterprise software solutions.
Kobor.ai Restaurant AI
AI-powered restaurant operations platform that turns existing security cameras into intelligent service monitors. Deployed across Özsüt's 150+ location franchise network, the system uses computer vision to detect customer attention signals, track table status, and route voice commands to staff in real-time — integrating with existing POS systems with zero additional hardware investment.
Sentinel-X.ai Security
Multi-camera perimeter security system built on NVIDIA DeepStream, ingesting up to 16 IP camera streams through GStreamer pipelines on Jetson Orin Nano edge nodes. Custom-trained ReID and behavior-analysis models detect intrusion, loitering, and tailgating in real time, with TensorRT FP16 optimization keeping per-stream latency below 20 ms. An MQTT event bus pushes alerts to a React command dashboard, validated through a 90-day pilot before full-site production rollout.
Warehouse Vision System
Edge-deployed computer vision for package tracking, inventory counting, and route optimization across a 12,000 m² warehouse floor. Six Jetson AGX Orin nodes run DeepStream pipelines processing ceiling-mounted IP cameras, while ESP32-S3 microcontrollers on custom PCBs handle barcode-trigger sensors and conveyor-gate signals over MQTT. We collected and annotated 45,000 package images on-site, then used TensorRT pruning and INT8 quantization to hit real-time throughput on every node.
Predictive Maintenance AI
IoT sensor network using custom-designed PCBs built around ESP32-S3 modules, capturing vibration, temperature, current-draw, and acoustic data from 120 CNC machines at 1 kHz sampling rates. Sensor firmware streams data over MQTT to a TimescaleDB time-series store, where lightweight TensorFlow Lite models run anomaly detection at the edge. The system predicts bearing and spindle failures 48–72 hours in advance, cutting unplanned downtime by 34% in the first six months.
Fleet Management Platform
GPS and telemetry platform for a 200-vehicle logistics fleet, powered by custom PCBs with ESP32 modules, u-blox GNSS receivers, and CAN-bus adapters. Each unit streams position, fuel level, and engine diagnostics over LTE-M to a Node.js ingest service backed by PostgreSQL with PostGIS. The React dashboard provides live map tracking, geofence alerts, route replay, and driver-behavior scoring — reducing fuel costs by 12% and improving delivery-window compliance to 96%.
Facial Recognition Access
Sub-200 ms facial recognition access control deployed on Jetson Orin Nano edge devices at building entry points, using ArcFace embeddings optimized through TensorRT FP16. GStreamer pipelines handle camera ingestion with infrared and visible-light dual-sensor fusion for anti-spoofing. We enrolled 2,400 employees through a secure on-premise pipeline with no cloud dependency, achieving a 99.92% true-accept rate at a 0.001% false-accept threshold across varying lighting conditions.
Production Line Analytics
Real-time OEE and cycle-time analytics dashboard ingesting data from 8 GStreamer camera feeds processed on Jetson AGX Orin via DeepStream, combined with PLC signals from the shop floor. A Next.js frontend with D3.js visualizations and TimescaleDB continuous aggregates delivers per-station efficiency metrics, bottleneck detection, and shift-comparison reports. The system identified a 14% throughput improvement opportunity within the first month by pinpointing micro-stoppages invisible to manual observation.
Smart Warehouse Robotics
Autonomous mobile robot navigation system combining Jetson AGX Orin vision processing with ROS2 and LiDAR-based SLAM for an 8,000 m² warehouse. DeepStream pipelines on the robots detect pallets, obstacles, and human workers in real time, while ESP32-based custom PCBs bridge the robot control bus with warehouse management signals over MQTT. We built the synthetic training dataset using domain randomization in NVIDIA Isaac Sim, then transferred models to physical robots with only 200 hours of real-world fine-tuning data.
Retail Video Analytics
Customer flow and heatmap analytics for a multi-store retail chain, running NVIDIA DeepStream on Jetson Orin Nano nodes processing 6 IP cameras per location. TensorRT-optimized person detection and tracking models generate dwell-time, queue-length, and zone-transition metrics stored in PostgreSQL. A React analytics dashboard lets store managers compare foot-traffic patterns across locations and time periods, resulting in a 9% increase in conversion rate after layout changes informed by the data.
Ready to Start Your Project?
Let's discuss how we can help transform your business with AI-powered solutions.
Get in Touch