Fix Flann compilation under nvcc + NEON

All <arm_neon.h> includes in core/cv_cpu_dispatch.h are protected by an
ifndef __CUDACC__ to prevent attempting to use neon intrinsics when
compiling cuda kernels (.cu) -- this prevents hard errors such as
  error: identifier "__builtin_neon_qi" is undefined

Add this same protection to flann/dist.h to fix compilation involving
flann.hpp.

modules/flann/include/opencv2/flann/dist.h

@@ -47,7 +47,7 @@ typedef unsigned __int64 uint64_t;
 # include <Intrin.h>
 #endif
 
-#ifdef __ARM_NEON__
+#if defined(__ARM_NEON__) && !defined(__CUDACC__)
 # include "arm_neon.h"
 #endif
 
@@ -425,7 +425,7 @@ struct Hamming
     ResultType operator()(Iterator1 a, Iterator2 b, size_t size, ResultType /*worst_dist*/ = -1) const
     {
         ResultType result = 0;
-#ifdef __ARM_NEON__
+#if defined(__ARM_NEON__) && !defined(__CUDACC__)
         {
             uint32x4_t bits = vmovq_n_u32(0);
             for (size_t i = 0; i < size; i += 16) {