日別アーカイブ: 2023年12月13日

研究進捗

週報(SUN YUYA)

コメントする

We find a lot of methods of re-detection about Long term object tracking.

1 . ‘Skimming-Perusal’ Tracking: A Framework for Real-Time and Robust Long-term Tracking

The  re-detection method:

After obtaining the best candidate in each frame, our tracker treats the tracked object as present or absent based on its confidence score and then determines the search state (local search or global search) in the next frame.

Key: Training a deep network(Verifier).

similarity

2 . SiamX: An Efficient Long-term Tracker Using Cross-level Feature Correlation and Adaptive Tracking Scheme

The  re-detection method:

Exploiting threshold score.

3 . Combining complementary trackers for enhanced long-term visual object tracking

Running two trackers.

Training a deep network to decide when to re-detect.

 

 

4 . GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequences

Background motion estimation to predict location.

Evaluating two bboxes.

 

4 . High-Performance Long-Term Tracking with Meta-Updater

input: socre, response map,  target object, template

model: lstm

output: score

 5. MFT: Long-Term Tracking of Every Pixel

Optical flow is very important.

 

 6. Multi-Template Temporal Siamese Network for Long-Term Object Tracking

Predicting trajectoyies.

The  re-detection method:

Input: distance error

Output: Reliability Score

 7. Multi-Template Temporal Siamese Network for Long-Term Object Tracking

Predicting trajectoyies.

The  re-detection method:

Input: distance error

Output: Reliability Score

 

8. Robust Long-Term Object Tracking via Improved Discriminative Model Prediction

We augment various backgrounds that are not included in the search area to train a more robust model in the background clutter.

 

9. Robust Long-Term Object Tracking via Improved Discriminative Model Prediction

We augment various backgrounds that are not included in the search area to train a more robust model in the background clutter.

 

10. Target-Aware Tracking with Long-term Context Attention

The  re-detection method:

P-mean_score：

        score_list.append(out[“conf_score”])
        score_num+=1
        if score_num==10:
            n=score_num
            p_mean=0.0
            for i in range(n):
                for j in range(i,n):
                    p_mean+=(score_list[i]/(j+1))
            p_mean=(p_mean/n)
            score_num=0
            score_list=[]
            if p_mean<=0.58 :#and idx%5==0:
                print(“global start ! seq_name : “,seq_name, ” “,frame)
                out= global_tracker.track(image, info=None)
                boxes[frame, :] = out[“target_bbox”]
                local_tracker.state=boxes[frame, :]
Threshold：

11. Unifying Short and Long-Term Tracking with Graph Hierarchies

Difficult to understand.