因为PCL在Jetson上无法使用CUDA进行点云的加速处理,所以我们开发了基于CUDA的点云处理库CUDA-PCL。 可以从这里获得相关的库和实例代码。
class cudaICP { public: /* nPCountM and nQCountM are the maximum of count for input clouds They are used to pre-allocate memory. */ cudaICP(int nPCountM, int nQCountM, cudaStream_t stream = 0); ~cudaICP(void); /* cloud_target = transformation_matrix *cloud_source When the Epsil...