Craniovertebral junction (CVJ) is one of the more complex parts of the spinal column. It provides mobility to the cranium and houses the spinal cord. In a healthy subject, the CVJ contributes 25% of the flexion–extension motion and 50% of the axial rotation of the neck. This work reports instrumentation development and results for evaluating implant performance in the stabilized CVJ after surgical procedures. Typically, some bony parts of the vertebrae causing compression to the spinal cord are removed and subsequently stabilized by the instrumenting implant in the CVJ. Pose estimation of the Cadaveric CVJ region is estimated using a monocular vision-based setup. The cervical spine’s first three vertebrae surround the CVJ area, where most cervical spine mobility originates. We aim to evaluate the performance of vision-based intervertebral motion estimation of the Cadaver’s CVJ in the Indian population, particularly in older people. A series of tests were performed on the Cadaver’s CVJ to evaluate the vision system-based motion estimation performance.

This article discusses the intervertebral motion present in the craniovertebral junction (CVJ) region. The CVJ region is bounded by the first three vertebras from the spinal column. It helps in bringing most of the neck motion. Intervention in this region requires surgery in which an implant is placed to stabilize the whole system. The various available implants need to undergo performance evaluation as their performance varies from region and anatomical diversity. For the Indian population, we are targeting to evaluate the performance of such an implant, testing it into a cadaver. The region of interest will be loaded as per the loading condition of an average human. Motion in these regions is evaluated using the camera. A preliminary test was done on a saw bone model of CVJ to assess the performance of segmentation methods. Multiple such ArUco markers are used to increase pose accuracy further, and the pose of the entire board of multiple tags provides us with reliable pose estimation. The absolute error ranged from a minimum of 0.1 mm to a maximum of 16 mm. At the same time, the mean and median absolute errors were 3.8961 mm and 3.35 mm. By considering the absolute lengths, the percentage error showed the following trends. The percentage error was between 3.9168% and 0.0230%.

This paper proposes a vision-based kinematic analysis and kinematic parameters identification of the proposed architecture, designed to perform the object catching in the real-time scenario. For performing the inverse kinematics, precise estimation of the link lengths and other parameters needs to be present. Kinematic identification of Delta based upon Model10 implicit model with ten parameters using the iterative least square method is implemented. The loop closure implicit equations have been modelled. In this paper, a vision-based kinematic analysis of the Delta robots to do the catching is discussed. A predefined library of ArUco is used to get a unique solution of the kinematics of the moving platform with respect to the fixed base. The re-projection error while doing the calibration in the vision sensor module is 0.10 pixels. Proposed architecture interfaced with the hardware using the PID controller. Encoders are quadrature and have a resolution of 0.15 degrees embedded in the experimental setup to make the system closed-loop (acting as feedback unit).