xuduo35/staple

C++ implementation of staple algorithm for object tracking.

staple's Issues

移植到arm架构处理器上有什么方案么？

追踪效果很不错，想移植到arm处理器上，但是 算法里面用到了 SSE 的东西。查了一下ARM架构的处理不支持，不知道有没有什么替代方案？？

malloc.c:2368: sysmalloc: Assertion failed

bg_area.width 96 bg_area.height 95
fg_area.width 40 fg_area.height 39
area_resize_factor 1.5707 norm_bg_area.width 151 norm_bg_area.height 149
norm_target_sz.width 76 norm_target_sz.height 74
norm_pwp_search_area.width 150 norm_pwp_search_area.height 148
track: malloc.c:2368: sysmalloc: Assertion `(old_top == (((mbinptr) (((char *) &((av)->bins[((1) - 1) * 2])) - __builtin_offsetof (struct malloc_chunk, fd)))) && old_size == 0) || ((unsigned long) (old_size) >= (unsigned long)((((__builtin_offsetof (struct malloc_chunk, fd_nextsize))+((2 *(sizeof(size_t))) - 1)) & ~((2 *(sizeof(size_t))) - 1))) && ((old_top)->size & 0x1) && ((unsigned long) old_end & pagemask) == 0)' failed.
Aborted

I use SSE2NEON.h replaced sse function and run on my phone, The above error occurred

会考虑c++实现一个long-term的跟踪算法吗

会考虑c++实现一个long-term的跟踪算法吗
lct-tracker 等

Incorrect template created when target close to image border.

When the target is close to the image border the template created for the correlation filter and the histogram model is off, causing the tracker to drift after a few frames. This is due to the lefttopLimit and rightbottomLimit of STAPLE_TRACKER::getSubwindow, which clip subWindow and causing the aforementioned issue.

A quick solution is to pad subWindow accordingly by replicating the border pixels.

I managed to solve the problem like this, however I am not allowed to submit a PR, could I be given permission in order to share my solution?
Thanks in advance

segmentation fault

I compiled it in my Ubuntu 14.04 system(OpenCV 3.1). When it runs, it shows segmentation fault. The message is
...norm_pwp_search_area.width 150 norm_pwp_search_area.height 148
Segmentation fault (core dumped)
Any suggestion for the error? Thanks