use ndarray::{Array1, Array2};
pub const COCO_KP_SIGMAS: [f32; 17] = [
0.026, 0.025, 0.025, 0.035, 0.035, 0.079, 0.079, 0.072, 0.072, 0.062, 0.062, 0.107, 0.107, 0.087, 0.087, 0.089, 0.089, ];
pub const CANON_LEFT_HIP: usize = 11;
pub const CANON_RIGHT_HIP: usize = 12;
const VISIBILITY_THRESHOLD: f32 = 0.5;
const MIN_REFERENCE_EXTENT: f32 = 1e-6;
const OKS_FALLBACK_SIGMA: f32 = 0.07;
pub(crate) fn bounding_box_diagonal(
kp: &Array2<f32>,
visibility: &Array1<f32>,
num_joints: usize,
) -> f32 {
let mut x_min = f32::MAX;
let mut x_max = f32::MIN;
let mut y_min = f32::MAX;
let mut y_max = f32::MIN;
let mut any_visible = false;
for j in 0..num_joints {
if visibility[j] >= VISIBILITY_THRESHOLD {
let x = kp[[j, 0]];
let y = kp[[j, 1]];
x_min = x_min.min(x);
x_max = x_max.max(x);
y_min = y_min.min(y);
y_max = y_max.max(y);
any_visible = true;
}
}
if !any_visible {
return 0.0;
}
let w = (x_max - x_min).max(0.0);
let h = (y_max - y_min).max(0.0);
(w * w + h * h).sqrt()
}
pub fn canonical_torso_size(gt_kpts: &Array2<f32>, visibility: &Array1<f32>) -> Option<f32> {
let n = gt_kpts.shape()[0].min(visibility.len());
if CANON_LEFT_HIP < n
&& CANON_RIGHT_HIP < n
&& visibility[CANON_LEFT_HIP] >= VISIBILITY_THRESHOLD
&& visibility[CANON_RIGHT_HIP] >= VISIBILITY_THRESHOLD
{
let dx = gt_kpts[[CANON_LEFT_HIP, 0]] - gt_kpts[[CANON_RIGHT_HIP, 0]];
let dy = gt_kpts[[CANON_LEFT_HIP, 1]] - gt_kpts[[CANON_RIGHT_HIP, 1]];
let torso = (dx * dx + dy * dy).sqrt();
if torso > MIN_REFERENCE_EXTENT {
return Some(torso);
}
}
let diag = bounding_box_diagonal(gt_kpts, visibility, n);
if diag > MIN_REFERENCE_EXTENT {
Some(diag)
} else {
None
}
}
pub fn pck_canonical(
pred_kpts: &Array2<f32>,
gt_kpts: &Array2<f32>,
visibility: &Array1<f32>,
threshold: f32,
) -> (usize, usize, f32) {
let n = pred_kpts.shape()[0]
.min(gt_kpts.shape()[0])
.min(visibility.len());
let torso = match canonical_torso_size(gt_kpts, visibility) {
Some(t) => t,
None => return (0, 0, 0.0),
};
let dist_threshold = threshold * torso;
let mut correct = 0usize;
let mut total = 0usize;
for j in 0..n {
if visibility[j] < VISIBILITY_THRESHOLD {
continue;
}
total += 1;
let dx = pred_kpts[[j, 0]] - gt_kpts[[j, 0]];
let dy = pred_kpts[[j, 1]] - gt_kpts[[j, 1]];
if (dx * dx + dy * dy).sqrt() <= dist_threshold {
correct += 1;
}
}
let pck = if total > 0 {
correct as f32 / total as f32
} else {
0.0
};
(correct, total, pck)
}
pub fn oks_canonical(
pred_kpts: &Array2<f32>,
gt_kpts: &Array2<f32>,
visibility: &Array1<f32>,
) -> f32 {
let n = pred_kpts.shape()[0]
.min(gt_kpts.shape()[0])
.min(visibility.len());
let s = match canonical_torso_size(gt_kpts, visibility) {
Some(t) => t,
None => return 0.0,
};
let s_sq = s * s;
if s_sq <= 0.0 {
return 0.0;
}
let mut num = 0.0f32;
let mut den = 0.0f32;
for j in 0..n {
if visibility[j] < VISIBILITY_THRESHOLD {
continue;
}
den += 1.0;
let dx = pred_kpts[[j, 0]] - gt_kpts[[j, 0]];
let dy = pred_kpts[[j, 1]] - gt_kpts[[j, 1]];
let d_sq = dx * dx + dy * dy;
let k = if j < COCO_KP_SIGMAS.len() {
COCO_KP_SIGMAS[j]
} else {
OKS_FALLBACK_SIGMA
};
num += (-d_sq / (2.0 * s_sq * k * k)).exp();
}
if den > 0.0 {
num / den
} else {
0.0
}
}
#[cfg(test)]
mod consts_tests {
use super::*;
#[test]
fn metrics_core_consts_unchanged_from_literals() {
assert_eq!(VISIBILITY_THRESHOLD, 0.5_f32);
assert_eq!(MIN_REFERENCE_EXTENT, 1e-6_f32);
assert_eq!(OKS_FALLBACK_SIGMA, 0.07_f32);
assert_eq!(CANON_LEFT_HIP, 11);
assert_eq!(CANON_RIGHT_HIP, 12);
}
#[test]
fn visibility_threshold_boundary_is_inclusive() {
let gt = Array2::from_shape_vec(
(13, 2),
(0..13).flat_map(|j| [j as f32, 0.0]).collect::<Vec<_>>(),
)
.unwrap();
let pred = gt.clone();
let mk_vis = |v0: f32| {
let mut vis = Array1::<f32>::zeros(13);
vis[CANON_LEFT_HIP] = 1.0;
vis[CANON_RIGHT_HIP] = 1.0;
vis[0] = v0; vis
};
let (_, total_at, _) = pck_canonical(&pred, >, &mk_vis(0.5), 0.2);
assert_eq!(total_at, 3, "vis == 0.5 must be INCLUDED (>=)");
let (_, total_below, _) = pck_canonical(&pred, >, &mk_vis(0.499), 0.2);
assert_eq!(total_below, 2, "vis < 0.5 must be EXCLUDED");
}
#[test]
fn degenerate_extent_below_floor_is_unscoreable() {
let gt = Array2::<f32>::zeros((13, 2));
let pred = gt.clone();
let mut vis = Array1::<f32>::zeros(13);
vis[CANON_LEFT_HIP] = 1.0;
vis[CANON_RIGHT_HIP] = 1.0;
assert!(canonical_torso_size(>, &vis).is_none());
assert_eq!(pck_canonical(&pred, >, &vis, 0.2), (0, 0, 0.0));
assert_eq!(oks_canonical(&pred, >, &vis), 0.0);
}
}