generic-library/opencv
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

cv::cvtColor (HLS2RGB CV_8U)

Browse Source
This commit is contained in:
Ilya Lavrenov 2014-10-07 15:37:21 +00:00
parent c173d9fa18
commit 71c3e67cb2
1 changed files with 65 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
modules/imgproc/src/color.cpp
View File

@ -3371,7 +3371,13 @@ struct HLS2RGB_b
HLS2RGB_b(int _dstcn, int _blueIdx, int _hrange)
: dstcn(_dstcn), cvt(3, _blueIdx, (float)_hrange)
{}
{
#if CV_NEON
v_scale_inv = vdupq_n_f32(1.f/255.f);
v_scale = vdupq_n_f32(255.f);
v_alpha = vdup_n_u8(ColorChannel<uchar>::max());
#endif
}
void operator()(const uchar* src, uchar* dst, int n) const
{
@ -3382,8 +3388,29 @@ struct HLS2RGB_b
for( i = 0; i < n; i += BLOCK_SIZE, src += BLOCK_SIZE*3 )
{
int dn = std::min(n - i, (int)BLOCK_SIZE);
j = 0;
for( j = 0; j < dn*3; j += 3 )
#if CV_NEON
for ( ; j <= (dn - 8) * 3; j += 24)
{
uint8x8x3_t v_src = vld3_u8(src + j);
uint16x8_t v_t0 = vmovl_u8(v_src.val[0]),
v_t1 = vmovl_u8(v_src.val[1]),
v_t2 = vmovl_u8(v_src.val[2]);
float32x4x3_t v_dst;
v_dst.val[0] = vcvtq_f32_u32(vmovl_u16(vget_low_u16(v_t0)));
v_dst.val[1] = vmulq_f32(vcvtq_f32_u32(vmovl_u16(vget_low_u16(v_t1))), v_scale_inv);
v_dst.val[2] = vmulq_f32(vcvtq_f32_u32(vmovl_u16(vget_low_u16(v_t2))), v_scale_inv);
vst3q_f32(buf + j, v_dst);
v_dst.val[0] = vcvtq_f32_u32(vmovl_u16(vget_high_u16(v_t0)));
v_dst.val[1] = vmulq_f32(vcvtq_f32_u32(vmovl_u16(vget_high_u16(v_t1))), v_scale_inv);
v_dst.val[2] = vmulq_f32(vcvtq_f32_u32(vmovl_u16(vget_high_u16(v_t2))), v_scale_inv);
vst3q_f32(buf + j + 12, v_dst);
}
#endif
for( ; j < dn*3; j += 3 )
{
buf[j] = src[j];
buf[j+1] = src[j+1]*(1.f/255.f);
@ -3391,7 +3418,38 @@ struct HLS2RGB_b
}
cvt(buf, buf, dn);
for( j = 0; j < dn*3; j += 3, dst += dcn )
j = 0;
#if CV_NEON
for ( ; j <= (dn - 8) * 3; j += 24, dst += dcn * 8)
{
float32x4x3_t v_src0 = vld3q_f32(buf + j), v_src1 = vld3q_f32(buf + j + 12);
uint8x8_t v_dst0 = vqmovn_u16(vcombine_u16(vqmovn_u32(cv_vrndq_u32_f32(vmulq_f32(v_src0.val[0], v_scale))),
vqmovn_u32(cv_vrndq_u32_f32(vmulq_f32(v_src1.val[0], v_scale)))));
uint8x8_t v_dst1 = vqmovn_u16(vcombine_u16(vqmovn_u32(cv_vrndq_u32_f32(vmulq_f32(v_src0.val[1], v_scale))),
vqmovn_u32(cv_vrndq_u32_f32(vmulq_f32(v_src1.val[1], v_scale)))));
uint8x8_t v_dst2 = vqmovn_u16(vcombine_u16(vqmovn_u32(cv_vrndq_u32_f32(vmulq_f32(v_src0.val[2], v_scale))),
vqmovn_u32(cv_vrndq_u32_f32(vmulq_f32(v_src1.val[2], v_scale)))));
if (dcn == 4)
{
uint8x8x4_t v_dst;
v_dst.val[0] = v_dst0;
v_dst.val[1] = v_dst1;
v_dst.val[2] = v_dst2;
v_dst.val[3] = v_alpha;
vst4_u8(dst, v_dst);
}
else
{
uint8x8x3_t v_dst;
v_dst.val[0] = v_dst0;
v_dst.val[1] = v_dst1;
v_dst.val[2] = v_dst2;
vst3_u8(dst, v_dst);
}
}
#endif
for( ; j < dn*3; j += 3, dst += dcn )
{
dst[0] = saturate_cast<uchar>(buf[j]*255.f);
dst[1] = saturate_cast<uchar>(buf[j+1]*255.f);
@ -3404,6 +3462,10 @@ struct HLS2RGB_b
int dstcn;
HLS2RGB_f cvt;
#if CV_NEON
float32x4_t v_scale, v_scale_inv;
uint8x8_t v_alpha;
#endif
};