how detect multiple object on same image

[janaka1984]

hi,

I have used following example https://huangying-zhan.github.io/2016/09/22/detection-faster-rcnn.html#Training%20on%20new%20dataset.

it can detect basketball, but I need to detect person also.
To do that I used person dataset with basketball dataset and changed train.txt and classes in basketball.py file

but it can not detect both object at once

what i need to change ?

thanks

[sulth]

Have you got solution for multiple object detection within 1 frame.Please share me the tips.

[janaka1984]

hi sulth,

call following block of code on main()

im = im[:, :, (2, 1, 0)]
fig, ax = plt.subplots(figsize=(12, 12))
 ax.imshow(im, aspect='equal')


for cls_ind, cls in enumerate(CLASSES[1:]):
        cls_ind += 1 # because we skipped background
        cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
        cls_scores = scores[:, cls_ind]
        dets = np.hstack((cls_boxes,cls_scores[:, np.newaxis])).astype(np.float32)
        keep = nms(dets, NMS_THRESH)
        dets =  dets[keep, :]
        vis_detections(ax, cls, dets,  thresh=CONF_THRESH)

def vis_detections(ax, class_name , dets, thresh=0.5):    
"""Draw detected bounding boxes."""
    inds = np.where(dets[:, -1] >= thresh)[0]
    print(inds)

    if len(inds) == 0:
          return
    for i in inds:
        bbox = dets[i, :4]
        score = dets[i, -1]
        print(bbox[0],bbox[1],bbox[2],bbox[3])
        ax.add_patch(
                     plt.Rectangle((bbox[0], bbox[1]),
                     bbox[2] - bbox[0],
                     bbox[3] - bbox[1], fill=False,
                     edgecolor='red', linewidth=3.5)
        )
        ax.text(bbox[0], bbox[1] - 2,
                '{:s} {:.3f}'.format(class_name, score),
                bbox=dict(facecolor='blue', alpha=0.5),
                fontsize=14, color='white')

    ax.set_title(('{} detections with '
                  'p({} | box) >= {:.1f}').format(class_name, class_name,  thresh), fontsize=14)
    plt.draw()

i hope you will get out put as you expect, try it :)

[sulth]

Yes.I got it.Thanks alot:)

[aakarshmalhotra]

Hi @janaka1984

I can see that you have followed the blog:
https://huangying-zhan.github.io/2016/09/22/detection-faster-rcnn.html#Training%20on%20new%20dataset

I am trying to reproduce the same results, however, I can't find the codes for basketball.py, basketball_eval.py and any other files for using this dataset. However, I have downloaded the dataset. Can you please guide me through this.

Thanks in advance.

[Niladri365]

I am looking for basketball.py and basketball_eval.py code. The annotations are also in .xml format instead of .txt format as INRIA person dataset. Would some body guide me in this regard?

[aakarshmalhotra]

Hi @Niladri365

You can find these files here:
https://github.com/Huangying-Zhan/py-faster-rcnn/tree/master/lib/datasets

Regards

[Niladri365]

Thanks a lot...

[Ram-Godavarthi]

@janaka1984 @sulth Can you share me the demo code where changes needs to done for getting 2 objects detection on single frame?. I tried your @janaka1984 solution. but i did not get it..
Could you please help me out..

Thank You