Rafael Advanced Defense Systems Ltd, a leading Israel-based defense technology company has unveiled its new Automatic Target Recognition (ATR) capability for its SPICE-250, a GPS-guided air-droppable unguided bombs.
Based on autonomous electro-optic Scene-Matching Algorithms, the missiles are capable of moving-Target-Detection using AI and deep learning algorithms.
Belonging to the family of autonomous air-to-ground weapon system with high pin-point accuracy, the technology will help SPICE-250 to further improve its target identification before the strike and is operational in GPS-denied conditions. This feature is made possible its scene-matching algorithms, which uploads the terrain data on to the device and by combining it with real-time electro-optic imagery, notes a leading defense portal. Further, the deep-learning will equip the missile with target identification and the ability to distinguish terrain and objects based on the 3D models and algorithms.
Sign up for your weekly dose of what's up in emerging technology.
“The deep-learning algorithm is indifferent to the actual data fed to it for modelling targets of interest and embedding their pertaining characteristics into the system. However, the more the data used for modelling is representative of the target of interest, the more robust the recognition probability will be in real life,” Gideon Weiss, Rafael’s deputy general manager of marketing and business development said.
SPICE- 250, which weighs up to 75 kg, can be deployed under the wings of warplanes to target objects at a stand-off range of 100 km. Thus, when the pilot identifies the target and allocates weapon, it uses the ATR mode for detection and recognition of the targets.
“Each weapon homes-in on the predefined target, either autonomously or with a human-in-the-loop, aided by the ATR algorithm,” the company said in a press release.