US 12,080,064 B1
Camera apparatus and method for reducing latency in plant detection from time of image capture
Gunasekaran Srinivasan, Thiruvalam (IN); Dhivakar Kanagaraj, Karur (IN); Pranav M P, Bengaluru (IN); Raghul Raghu, Madurai (IN); Prakash Mathews Pothen, Thiruvalla (IN); and S Prajwal, Karnataka (IN)
Assigned to Tartan Aerial Sense Tech Private Limited, Bangalore (IN)
Filed by Tartan Aerial Sense Tech Private Limited, Bangalore (IN)
Filed on Feb. 23, 2024, as Appl. No. 18/586,401.
Claims priority of application No. 202341071593 (IN), filed on Oct. 19, 2023.
Int. Cl. G06V 20/00 (2022.01); G06T 3/4015 (2024.01); G06V 10/25 (2022.01); G06V 10/82 (2022.01); G06V 20/10 (2022.01); H04N 9/73 (2023.01); H05K 1/18 (2006.01)
CPC G06V 20/188 (2022.01) [G06T 3/4015 (2013.01); G06V 10/25 (2022.01); G06V 10/82 (2022.01); H04N 9/73 (2013.01); H05K 1/181 (2013.01); G06V 2201/07 (2022.01); H05K 2201/10121 (2013.01); H05K 2201/10151 (2013.01); H05K 2201/10159 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A camera apparatus, comprising:
a central processing unit (CPU) configured to:
capture raw image sensor data of a field-of-view (FOV) of an agricultural field using an image sensor;
concurrently execute a plurality of different image transformation operations in a single pass on the captured raw image sensor data to obtain a processed image output, based on an one-time read of pixel values of the captured raw image sensor data; and
push the processed image output in a shared memory accessible to a plurality of application nodes in the camera apparatus, and
a graphical processing unit (GPU) configured to:
execute a first neural network model on the processed image output accessed from the shared memory to detect one or more foliage regions in the processed image output and concomitantly execute a second neural network model on the processed image output accessed from the shared memory to detect one or more crop plants in the processed image output, wherein the plurality of application nodes in the camera apparatus comprises at least the first neural network model and the second neural network model.