Carried object detection using star skeleton with adaptive centroid and time series graph

Chayanurak, Rawin; Cooharojananone, Nagul; Satoh, Shin’ichi; Lipikorn, Rajalida

doi:10.1109/icosp.2010.5655765

Cited by 11 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Carried objects are mismatching parts in the person silhouette when compared with the best matching dynamic shape model. In the work of Chayanurak et al [5], the human silhouette is represented by a star skeleton.…”

Section: Related Workmentioning

confidence: 99%

From superpixel to human shape modelling for carried object detection

Ghadiri

Bergevin

Bilodeau

2019

Pattern Recognition

View full text Add to dashboard Cite

Detecting carried objects is one of the requirements for developing systems to reason about activities involving people and objects. We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales. Initially, a foreground mask in a video frame is segmented into multi-scale superpixels. Then the human-like regions in the segmented area are identified by matching a set of extracted features from superpixels against learned features in a codebook. A carried object probability map is generated using the complement of the matching probabilities of superpixels to human-like regions and background information. A group of superpixels with high carried object probability and strong edge support is then merged to obtain the shape of the carried object. We applied our method to two challenging datasets, and results show that our method is competitive with or better than the state-of-the-art.

show abstract

Section: Related Workmentioning

confidence: 99%

From superpixel to human shape modelling for carried object detection

Ghadiri

Bergevin

Bilodeau

2019

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…There are three main schools of thought to detect carried object (CO), namely (i) analysing the human shape to detect anomalies [1,2,3,4], (ii) learning models for each type of carried object [5,6,7] and (iii) analysing difference in human gait and motion patterns [1,8,9]. Learning a model for each object type is quite challenging due to the variety of object type carried by a person.…”

Section: Introductionmentioning

confidence: 99%

Spatio-Temporal Consistency to Detect and Segment Carried Objects

Ghadiri

Bergevin

Bilodeau

2017

Procedings of the British Machine Vision Conference 2017

View full text Add to dashboard Cite

We present a new method to detect carried objects and to segment them accurately after detection. The proposed method includes several contributions: first, a new superpixelbased descriptor is proposed to identify carried object-like candidate regions using human shape modelling. Second, integrating spatio-temporal information of candidate regions to detect carried objects. We exploit the consistency of recurring carried object candidates viewed over time to detect the final carried object locations based on their motion and location priors. Last, the detected carried object regions are accurately segmented. Compared to existing methods, our approach is not only focusing on detecting carried objects. It takes a step forward and accurately segment them. Our method to carried object segmentation couples local appearance cues with location priors of the detected carried objects to produce accurate segmentation. Experimental evaluation on two datasets demonstrates that both our carried object detection and segmentation methods significantly outperform competing algorithms.

show abstract

“…Yuan Bo et al improve [11] using uses fuzzy c-means algorithm [12]. [13] uses pose preserving dynamic shape models, [14] uses star skeleton with adaptive centroid and time series graph, [15] uses ratio histogram, [16] use body main axis to present the detection features.…”

Section: Introductionmentioning

confidence: 99%

A method of carried object detection based on key posture of silhouette

Wang

2015

2015 11th International Conference on Natural Computation (ICNC)

View full text Add to dashboard Cite

In this paper, we present a novel carried object detection method based on the key postures which is extracted through locating the key point on the gait cycle curve. The key postures which are conducive to detect the carried object are the silhouettes in sequence. Different carried type is corresponding to the different key postures. For each key posture, the deviation between the reference axis and the center line and the variance of the lower-limb width are adopted to represent features. We test our method on two databases. The results show that the method based on key postures can not only reduce the computation, but also represent features very accurately, and our method is effective.

show abstract

Carried object detection using star skeleton with adaptive centroid and time series graph

Cited by 11 publications

References 7 publications

From superpixel to human shape modelling for carried object detection

From superpixel to human shape modelling for carried object detection

Spatio-Temporal Consistency to Detect and Segment Carried Objects

A method of carried object detection based on key posture of silhouette

Contact Info

Product

Resources

About