add native 3D object detection using ZED SDK optimized models

Add engines::ZedNative class wrapping ZED SDK's TensorRT-optimized
object detection. On every frame grab, detected objects (label,
confidence, 3D position, 2D/3D bounding boxes) are serialized as a
flat float32 array and sent as a new "objects" dora output with
frame_id correlation to image_bgr.

Extract shared env-var helpers into src/util/env.h and expose
sl::Camera& via Camera::handle() for engine access.

Closes #3

src/engines/zed_native.cc

@@ -0,0 +1,95 @@
+#include "engines/zed_native.h"
+#include "util/env.h"
+
+#include <iostream>
+#include <string>
+
+namespace {
+
+sl::OBJECT_DETECTION_MODEL parse_detection_model(const std::string& model) {
+    if (model == "MULTI_CLASS_BOX_FAST") {
+        return sl::OBJECT_DETECTION_MODEL::MULTI_CLASS_BOX_FAST;
+    }
+    if (model == "MULTI_CLASS_BOX_ACCURATE") {
+        return sl::OBJECT_DETECTION_MODEL::MULTI_CLASS_BOX_ACCURATE;
+    }
+    return sl::OBJECT_DETECTION_MODEL::MULTI_CLASS_BOX_MEDIUM;
+}
+
+} // namespace
+
+namespace engines {
+
+DetectionConfig DetectionConfig::from_env() {
+    DetectionConfig c;
+    c.model = util::get_env_str("ZED_DETECTION_MODEL", c.model);
+    c.confidence_threshold = util::get_env_float("ZED_DETECTION_CONFIDENCE", c.confidence_threshold);
+    c.tracking = util::get_env_bool("ZED_DETECTION_TRACKING", c.tracking);
+    return c;
+}
+
+ZedNative::ZedNative(const DetectionConfig& config) : config_(config) {
+    det_params_.detection_model = parse_detection_model(config_.model);
+    det_params_.enable_tracking = config_.tracking;
+    det_params_.enable_segmentation = false;
+
+    det_rt_params_.detection_confidence_threshold = config_.confidence_threshold;
+}
+
+void ZedNative::enable(sl::Camera& camera) {
+    if (config_.tracking) {
+        sl::PositionalTrackingParameters tracking_params;
+        sl::ERROR_CODE err = camera.enablePositionalTracking(tracking_params);
+        if (err != sl::ERROR_CODE::SUCCESS) {
+            std::cerr << "Failed to enable positional tracking: "
+                      << sl::toString(err) << std::endl;
+        }
+    }
+
+    std::cout << "Object Detection: loading model (" << config_.model << ")..." << std::endl;
+    sl::ERROR_CODE err = camera.enableObjectDetection(det_params_);
+    if (err != sl::ERROR_CODE::SUCCESS) {
+        std::cerr << "Failed to enable object detection: "
+                  << sl::toString(err) << std::endl;
+        return;
+    }
+    std::cout << "Object Detection: model loaded." << std::endl;
+}
+
+void ZedNative::detect(sl::Camera& camera) {
+    detected_.clear();
+
+    sl::ERROR_CODE err = camera.retrieveObjects(raw_objects_, det_rt_params_);
+    if (err != sl::ERROR_CODE::SUCCESS) {
+        return;
+    }
+
+    for (const auto& obj : raw_objects_.object_list) {
+        DetectedObject det{};
+        det.label_id = static_cast<int>(obj.label);
+        det.confidence = obj.confidence;
+
+        det.position[0] = obj.position.x;
+        det.position[1] = obj.position.y;
+        det.position[2] = obj.position.z;
+
+        for (int i = 0; i < 4 && i < static_cast<int>(obj.bounding_box_2d.size()); i++) {
+            det.bounding_box_2d[i * 2 + 0] = obj.bounding_box_2d[i].x;
+            det.bounding_box_2d[i * 2 + 1] = obj.bounding_box_2d[i].y;
+        }
+
+        for (int i = 0; i < 8 && i < static_cast<int>(obj.bounding_box.size()); i++) {
+            det.bounding_box_3d[i * 3 + 0] = obj.bounding_box[i].x;
+            det.bounding_box_3d[i * 3 + 1] = obj.bounding_box[i].y;
+            det.bounding_box_3d[i * 3 + 2] = obj.bounding_box[i].z;
+        }
+
+        detected_.push_back(det);
+    }
+}
+
+const std::vector<DetectedObject>& ZedNative::objects() const {
+    return detected_;
+}
+
+} // namespace engines