yannzyl/apollo-note

Note for Apollo 3.0 perception, prediction and planning modules

apollo-note's Issues

关于分割后并查集聚类中的Traverse函数

@YannZyl 您好！非常感谢您的分享，学到很多。有一个问题问一下，在obstacles_lidar_2_cnn.md中分析的并查集部分中的Traverse函数，“每棵树只有一条path的is_center=true"， 其他都是false，导致后续合并时一棵树只与另一棵树的指定支路去合并。” 不太明白为什么不把所有的path的is_center设为true，这样相近的所有树及分支都能够合并，只与一个path合并的话，不会漏掉与这一个path距离远而与其他path距离较近的同一个物体上的点吗？如果我想尝试合并所有相近的树和分支，是不是应该把if (x->traversed == 2)改为if(x->traversed == 2 || x->traversed == 1)?
谢谢！

计算单元格的8个属性的问题

您好，我在看到计算单元格8个属性的代码时候，不是应该用映射之后的单元格吗？为什么又把坐标转到以激光雷达为中心，前后左右各60这里来了呢？我计算出来的center_x的范围是（-60，60），不是应该用width x height 上的单元格吗？麻烦您了

How to convert minbox direction center to quarterion?

Hi, may I ask how to convert the minbox direction and center into a Pose (with quarterion and dimension)?

Simply I know the l,w,h, means, but what does direction means? Coordinates terms to lidar origin? How to get the pose of obstacle in quarterion?

HM

数据关联部分，在ConnectedComponentAnalysis中，得到的components二维向量中，每一行为一个子图的组成元素，这个子图是如何划分的，有点不明白

Apollo-Note/docs/perception/obstacles_lidar_4_hmtrack.md ComputeAssociateMatrixhas issue for advice

Thank you very much for your summary and share.I would like to ask two questions in the Apollo/ Percetion/LIdar module:
The following source code, the path for "modules/perception/obstacle/lidar/tracker/hm_tracker/track_object_distance. cc" , when lidar track ComputeAssociateMatrixhas five factors, including: location_distance,direction_distance,bbox_size_distance,point_num_distance,histogram_distance. I want to ask whether there is any selection basis for selecting the 5 parameters for weighting. There are 5 default weights s_location_distance_weight_, s_direction_distance_weight_, s_bbox_size_distance_weight_, s_point_num_distance_weight_, s_histogram_distance_weight_ are where the selection is given**?
float TrackObjectDistance::ComputeDistance( ObjectTrackPtr track, const Eigen::VectorXf& track_predict, const std::shared_ptr<TrackedObject>& new_object) { // Compute distance for given trakc & object ....... float result_distance = s_location_distance_weight_ * location_distance + s_direction_distance_weight_ * direction_distance + s_bbox_size_distance_weight_ * bbox_size_distance + s_point_num_distance_weight_ * point_num_distance + s_histogram_distance_weight_ * histogram_distance; return result_distance; }

In the source code, association_(i, j) <= connected_threshold==4. What factors are considered in the selection of this connected_threshold=4?

Looking forward to your reply and best wishes!

如何在训练中标注中心offset数据

您好，看到在CNN网络的输出中，由两项数据是表示中心偏移，想请问，如果自己标注数据训练，这个中心偏移该如何标注呢？

ConnectedComponentAnalysis这个函数在哪个文件嘞，只在match中看到了应用，没有找到函数体

Model used

Which model is used for traffic light perception ?