【VID】On the stability of video detection and Tracking

key point:

衡量视频检测框的稳定性指标,以及提升稳定性的方法评估
paper:https://arxiv.org/abs/1611.06467

1 Work

stability:16.11前,no prior Work
A novel evaluation Metric for video detection:
1)Accuracy:extended mAP
2)Stability:a)fragment Error; b)center position Error;c)scale and ratio error;
3)Stability Metric has low correlation with Accuracy Metric

2 Introduction

1)Detection

Certain Object detection(Face/hand/pedestrian)->General Object detection(DPM、region based methods[rich feature hierarchies for accurate Object detection and Semantic Segmentation][Fast R-CNN][Faster R-CNN][Spatial pyramid pooling in deep convolutional networks for visual Recognition] & direct regression methods[YOLO][SSD])

2)Video detection

1)use object class correlation and motion propagation,Rescore detections based on the tubelets generated by visual tracking->limited in post-processing stage.
2)integerate temporal context in end2end manner. A closely related area——video segmentation——use Conv-LSTM, capturing both temporal and spatial info.

3)MOT Algorithm

1)(Nearly) Online Algorithm[4,6,21]:try to associate existing targets with detections in recent frames after receiving the input image.
2)Offline Algorithms[2,30]:read in all frames

4)VID Metric

a)Accuracy
IoU and IoU threshold -> precision and recall curve by varying the threshold -> AP=Area Under Curve(AUC) of precision and recall curve -> mAUC over all classes
b)Stability
aa)Temporal Stability:measure the integrity of a trajectory
bb)Spatial Stability:measure how much detection box jitter around GT in a trajectory

3 Detection Stability

output detections match GT:Hungarian Algorithm。IOUs between them are weights of the bipartile graph.
φ=Ef + Ec + Er

1)Ef(Fragment Error)

1)Status change:Object is detected in previous frame but missed in current frame or missed in previous but detected in current frame
2)Ef=1/N * Sum[ Fk/(Tk - 1) ], N个trajectory,Tk 是第k个trajectory的长度,Fk是status change的数量。——Fragment Error在MOT评价中也存在,与这里的区别是Normalized by the trajectory length。

2)Ec(Center Position Error)

a)evaluate the change of center position in both horizontal and vertical directions.
b)BBox = (X,Y,W,H)
Ex,f,k = (Xp,f,k-Xg,f,k)/Wg,f,k
Ey,f,k = (Yp,f,k-Yg,f,k)/Hg,f,k
δx,k=std(Ex,f,k)
δy,k=std(Ey,f,k)
**δ是标准差(standard deviation)
Ec = 1/N
Sum[ δx,k + δy,k ]
因为bias已经在Accuracy Metric里考虑了,这里Ec只考虑variance of center deviation。

3)Er(Scale and Ratio Error)

1)Use square root of the area ratio to represent scale deviation;
2)BBox = (X,Y,W,H)
Es,f,k = sqrt[ (Wp,f,kHp,f,k)/(Wg,f,kHg,f,k) ]
Er,f,k = (Wp,f,k/Hp,f,k)/(Wg,f,k/Hg,f,k)
δs,k = std(Es,f,k )
δr,k = std(Er,f,k)
Er = 1/N*Sum[ δs,k + δr,k ]
同样focus on the variance instead of bias of the scale and ratio deviation.

4 Validation & Analysis

对比VID中bbox聚合aggregation(消除冗余)阶段的方法:
a)aggregation bbox within single frame(在单帧内聚合输出的检测框):representative method weighted NMS[Object detection via a multi-region and semantic segmentation-aware CNN model]
b)utilize the temporal context across frames:Motion Guided Propagation(MGP)[T-CNN: tubelets with convolutional neural networks for Object detection from videos] and object tracking[Forward-backward error:Automatic detection of Tracking failures]

*额外模型类型:利用不同class的correlation来抑制(suppress) False Positives——Multi-context suppression[T-CNN: tubelets with convolutional neural networks for Object detection from videos]

1)Weighted NMS

rather than only keeping the bounding box with highest score, we weighted average it with all the suppressed bounding boxes by their scores. It was first proposed in [Object detection via a multi-region and semantic segmentation-aware CNN model] to improve the mAP of still image detection. ——Also helpful to improve Stability[值得关注,NMS优化有助于提升框稳定性]

2)MGP

1)Insight:propagating detections to adjacent frames help recover FP(False Negative)
2)MGP takes raw bbox before aggregation, then propagates them bidirectionally across adjacent frames using optical flow.
3)the propagated bbox are treated equally as other detections, and use in aggregation.
***4) 为propagated bbox增加decay factor for detection score可以提高稳定性,decay factor和应用的数据集有关系

MGP能降低Fragment error.

3)Object Tracking: 调研用物体跟踪来smooth trajectory

1)选择Median Flow (MF)[Forward-backward Error:Automatic detection of tracking failures]——efficient and effective short term tracking method
2)不同于MGP,论文在bbox aggregation(NMS or weighted NMS)之后使用MF
3)只用MF smooth detection bbox,而不改变detection score,也不add new box;
4)高置信度的bbox->tracking->发现frame里的bbox和跟踪bbox IOU>0.5, 就average them as the final box;For the detections without any associated Tracking box,keep it unchanged。

MF能提升center Error,但会小幅降低Accuracy。

5 Stability & Accuracy:

1)No single best method that outperforms others in both Accuracy and Stability
2)Weighted NMS 在两者上都有提升,MF更多的是提升Stability。MGP提升Accuracy,尽管MF和MGP都是使用运动信息来指导detection [很有趣的结论]

©著作权归作者所有,转载或内容合作请联系作者
  • 序言:七十年代末,一起剥皮案震惊了整个滨河市,随后出现的几起案子,更是在滨河造成了极大的恐慌,老刑警刘岩,带你破解...
    沈念sama阅读 157,456评论 4 361
  • 序言:滨河连续发生了三起死亡事件,死亡现场离奇诡异,居然都是意外死亡,警方通过查阅死者的电脑和手机,发现死者居然都...
    沈念sama阅读 66,763评论 1 290
  • 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
    开封第一讲书人阅读 107,265评论 0 238
  • 文/不坏的土叔 我叫张陵,是天一观的道长。 经常有香客问我,道长,这世上最难降的妖魔是什么? 我笑而不...
    开封第一讲书人阅读 43,716评论 0 202
  • 正文 为了忘掉前任,我火速办了婚礼,结果婚礼上,老公的妹妹穿的比我还像新娘。我一直安慰自己,他们只是感情好,可当我...
    茶点故事阅读 52,071评论 3 286
  • 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
    开封第一讲书人阅读 40,435评论 1 212
  • 那天,我揣着相机与录音,去河边找鬼。 笑死,一个胖子当着我的面吹牛,可吹牛的内容都是我干的。 我是一名探鬼主播,决...
    沈念sama阅读 31,751评论 2 310
  • 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
    开封第一讲书人阅读 30,437评论 0 195
  • 序言:老挝万荣一对情侣失踪,失踪者是张志新(化名)和其女友刘颖,没想到半个月后,有当地人在树林里发现了一具尸体,经...
    沈念sama阅读 34,148评论 1 239
  • 正文 独居荒郊野岭守林人离奇死亡,尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 30,411评论 2 244
  • 正文 我和宋清朗相恋三年,在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 31,912评论 1 257
  • 序言:一个原本活蹦乱跳的男人离奇死亡,死状恐怖,灵堂内的尸体忽然破棺而出,到底是诈尸还是另有隐情,我是刑警宁泽,带...
    沈念sama阅读 28,281评论 2 252
  • 正文 年R本政府宣布,位于F岛的核电站,受9级特大地震影响,放射性物质发生泄漏。R本人自食恶果不足惜,却给世界环境...
    茶点故事阅读 32,913评论 3 234
  • 文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹,春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 26,020评论 0 8
  • 文/苍兰香墨 我抬头看了看天上的太阳。三九已至,却和暖如春,着一层夹袄步出监牢的瞬间,已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 26,776评论 0 192
  • 我被黑心中介骗来泰国打工, 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留,地道东北人。 一个月前我还...
    沈念sama阅读 35,462评论 2 269
  • 正文 我出身青楼,却偏偏与公主长得像,于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子,可洞房花烛夜当晚...
    茶点故事阅读 35,350评论 2 262

推荐阅读更多精彩内容